<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Mcp on AI Knowledge Base</title><link>https://learn-ai.blindshot.kz/source/mcp/</link><description>Recent content in Mcp on AI Knowledge Base</description><generator>Hugo</generator><language>en-us</language><atom:link href="https://learn-ai.blindshot.kz/source/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>Antitrust Policy</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/antitrust/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/antitrust/</guid><description>MCP Project Antitrust Policy for participants and contributors</description></item><item><title>Architecture</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/architecture/_overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/architecture/_overview/</guid><description/></item><item><title>Architecture overview</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/learn/architecture/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/learn/architecture/</guid><description>&lt;p&gt;The most important mental model here is the three-layer architecture: Host (the application), Client (the protocol handler), and Server (the capability provider). A common mistake is conflating the host and the client &amp;ndash; the host is the user-facing application (like Claude Desktop), while the client is an internal protocol component that maintains a 1:1 connection with a single server. Understanding this separation is essential before reading the specification or building anything.&lt;/p&gt;</description></item><item><title>Authorization</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/authorization/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/authorization/</guid><description>&lt;p&gt;The MCP authorization specification defines the OAuth 2.0-based flow that remote MCP servers use to authenticate clients, and it is the formal basis for everything the higher-level registry authentication guide simplifies. Focus on the required OAuth grant types, token scoping rules, and the metadata discovery mechanism that clients use to find a server&amp;rsquo;s authorization endpoint. A key gotcha is that the spec mandates specific OAuth metadata fields that many generic OAuth libraries do not populate by default, so you may need custom configuration even when using well-known auth frameworks. This is dense specification text best read alongside a working implementation for reference.&lt;/p&gt;</description></item><item><title>Authorization Extensions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/auth/overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/auth/overview/</guid><description>Supplementary authorization mechanisms for the Model Context Protocol</description></item><item><title>Build an MCP App</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/apps/build/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/apps/build/</guid><description>Getting started guide for building interactive UI applications with MCP Apps</description></item><item><title>Build an MCP client</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/build-client/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/build-client/</guid><description>Get started building your own client that can integrate with all MCP servers.</description></item><item><title>Build an MCP server</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/build-server/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/build-server/</guid><description>Get started building your own server to use in Claude for Desktop and other clients.</description></item><item><title>Build with Agent Skills</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/build-with-agent-skills/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/build-with-agent-skills/</guid><description>Use agent skills to guide AI coding assistants through MCP server design and implementation</description></item><item><title>Cancellation</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/utilities/cancellation/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/utilities/cancellation/</guid><description/></item><item><title>Completion</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/utilities/completion/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/utilities/completion/</guid><description/></item><item><title>Connect to local MCP servers</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/connect-local-servers/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/connect-local-servers/</guid><description>Learn how to extend Claude Desktop with local MCP servers to enable file system access and other powerful integrations</description></item><item><title>Connect to remote MCP Servers</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/connect-remote-servers/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/develop/connect-remote-servers/</guid><description>Learn how to connect Claude to remote MCP servers and extend its capabilities with internet-hosted tools and data sources</description></item><item><title>Contributing to MCP</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/contributing/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/contributing/</guid><description>How to contribute to the Model Context Protocol project</description></item><item><title>Contributor Communication</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/communication/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/communication/</guid><description>Communication strategy and framework for the Model Context Protocol community</description></item><item><title>Contributor Ladder</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/contributor-ladder/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/contributor-ladder/</guid><description>Roles, responsibilities, and advancement criteria for MCP contributors, from first contribution to Core Maintainer</description></item><item><title>Debugging</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/tools/debugging/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/tools/debugging/</guid><description>A comprehensive guide to debugging Model Context Protocol (MCP) integrations</description></item><item><title>Design Principles</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/design-principles/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/design-principles/</guid><description>The core design principles that guide the development of the Model Context Protocol.</description></item><item><title>Elicitation</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/client/elicitation/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/client/elicitation/</guid><description/></item><item><title>Enterprise-Managed Authorization</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/auth/enterprise-managed-authorization/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/auth/enterprise-managed-authorization/</guid><description>Centralized access control for MCP in enterprise environments via identity providers</description></item><item><title>Example Clients</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/clients/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/clients/</guid><description>A list of applications that support MCP integrations</description></item><item><title>Example Servers</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/examples/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/examples/</guid><description>A list of example servers and implementations</description></item><item><title>Extension Support Matrix</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/client-matrix/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/client-matrix/</guid><description>Which MCP clients implement which official extensions</description></item><item><title>Extensions Overview</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/overview/</guid><description>Optional extensions to the Model Context Protocol</description></item><item><title>Frequently Asked Questions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/faq/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/faq/</guid><description>&lt;p&gt;This FAQ addresses the practical edge cases that the other registry guides do not cover in depth, including questions about naming conflicts, transfer of ownership, and delisting policies. Read this after you have gone through the main registry overview and authentication guides, since many answers assume familiarity with those workflows. The sections on troubleshooting publishing failures are particularly valuable if you encounter cryptic errors during your first submission attempt.&lt;/p&gt;</description></item><item><title>Governance and Stewardship</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/governance/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/governance/</guid><description>Learn about the Model Context Protocol&amp;rsquo;s governance structure and how to participate in the community</description></item><item><title>Group Charter Template</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/charter-template/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/charter-template/</guid><description>Template for MCP Working Group and Interest Group charters.</description></item><item><title>How to Authenticate When Publishing to the Official MCP Registry</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/authentication/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/authentication/</guid><description>&lt;p&gt;Authentication is the first barrier you will hit when trying to publish an MCP server to the official registry, and getting it wrong means silent failures with unhelpful error messages. Focus on how GitHub-based identity verification works and the relationship between your GitHub account and registry publishing permissions. If you are building CI/CD pipelines for MCP server releases, read this before the GitHub Actions guide so you understand the credential flow that automation depends on.&lt;/p&gt;</description></item><item><title>How to Automate Publishing with GitHub Actions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/github-actions/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/github-actions/</guid><description>&lt;p&gt;Automating MCP server publishing through GitHub Actions eliminates manual release steps and ensures every tagged release reaches the registry consistently. The guide walks through workflow file configuration, secret management for registry credentials, and trigger conditions for version-based publishing. A common pitfall is misconfiguring the authentication token scope, which produces permissions errors that surface only at publish time rather than during the workflow setup. Read the authentication guide first to understand the credential requirements before wiring up the action.&lt;/p&gt;</description></item><item><title>Key Changes</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/changelog/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/changelog/</guid><description/></item><item><title>Lifecycle</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/lifecycle/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/lifecycle/</guid><description>&lt;p&gt;The lifecycle specification defines the three phases every MCP connection goes through: initialization, operation, and shutdown. Focus especially on the initialization handshake where client and server exchange capabilities &amp;ndash; getting this wrong is the most common source of connection failures. Note that the protocol version negotiation happens here too, so mismatched versions between client and server will fail fast at this stage rather than producing mysterious errors later.&lt;/p&gt;</description></item><item><title>Logging</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/utilities/logging/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/utilities/logging/</guid><description/></item><item><title>MCP Apps</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/apps/overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/apps/overview/</guid><description>Interactive UI applications that render inside MCP hosts like Claude Desktop</description></item><item><title>MCP Inspector</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/tools/inspector/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/tools/inspector/</guid><description>In-depth guide to using the MCP Inspector for testing and debugging Model Context Protocol servers</description></item><item><title>MCP Registry Aggregators</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/registry-aggregators/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/registry-aggregators/</guid><description/></item><item><title>MCP Registry Supported Package Types</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/package-types/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/package-types/</guid><description>&lt;p&gt;The MCP registry supports multiple package types and choosing the wrong one constrains how clients can discover and install your server. Understanding the distinction between npm packages, Docker images, and other supported formats is critical before you publish, because changing package type after initial publication creates migration headaches for existing consumers. Focus on the compatibility matrix between package types and host applications, since not every MCP client supports every format equally well.&lt;/p&gt;</description></item><item><title>OAuth Client Credentials</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/auth/oauth-client-credentials/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/extensions/auth/oauth-client-credentials/</guid><description>Machine-to-machine authentication for MCP using the OAuth 2.0 client credentials flow</description></item><item><title>Official MCP Registry Terms of Service</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/terms-of-service/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/terms-of-service/</guid><description/></item><item><title>Overview</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/_overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/_overview/</guid><description/></item><item><title>Overview</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/_overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/_overview/</guid><description/></item><item><title>Pagination</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/utilities/pagination/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/utilities/pagination/</guid><description/></item><item><title>Ping</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/utilities/ping/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/utilities/ping/</guid><description/></item><item><title>Progress</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/utilities/progress/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/utilities/progress/</guid><description/></item><item><title>Prompts</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/prompts/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/prompts/</guid><description>&lt;p&gt;Prompts are the least commonly used of the three MCP primitives, but they fill an important niche: reusable, parameterized templates that help users invoke common workflows. Think of them as saved recipes that combine a specific prompt structure with dynamic arguments. Unlike tools and resources, prompts are user-initiated &amp;ndash; the user explicitly selects a prompt from a menu rather than the model discovering it automatically. This makes them ideal for standardizing repetitive interactions like &amp;ldquo;summarize this codebase&amp;rdquo; or &amp;ldquo;review this PR.&amp;rdquo;&lt;/p&gt;</description></item><item><title>Publishing Remote Servers</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/remote-servers/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/remote-servers/</guid><description>&lt;p&gt;Remote servers represent a significant architectural shift from the local stdio-based MCP servers most developers start with, enabling cloud-hosted tools accessible over HTTP with persistent sessions. This guide covers the specific requirements for publishing remote servers to the registry, including endpoint URL configuration and health check expectations. Watch for the distinction between the server&amp;rsquo;s transport URL and its registry metadata URL, as confusing the two is a frequent source of registration failures. Read this after the general registry overview if you plan to deploy MCP servers as hosted services rather than local processes.&lt;/p&gt;</description></item><item><title>Quickstart: Publish an MCP Server to the MCP Registry</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/quickstart/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/quickstart/</guid><description>&lt;p&gt;Publishing your MCP server to the registry makes it discoverable by any MCP client, which is a critical step for adoption beyond your own projects. Focus on the metadata requirements (name, description, capabilities) because poorly described servers are effectively invisible in the registry. Note that the registry currently requires GitHub-based authentication and a specific package manifest format — read through the validation errors carefully if your first publish attempt fails, as the error messages are quite specific. Come to this doc after you have a working server from the build-server tutorial, since you need a functional server before publishing makes sense.&lt;/p&gt;</description></item><item><title>Resources</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/resources/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/resources/</guid><description>&lt;p&gt;Resources are how MCP servers expose data to the model without requiring the model to &amp;ldquo;call&amp;rdquo; anything &amp;ndash; think of them as files or documents the application can pull into context. The key distinction from tools is that resources are application-controlled (the host decides when to read them), while tools are model-controlled (the model decides when to invoke them). Pay attention to the URI-based addressing scheme, which lets clients discover and subscribe to resource updates. If your use case is primarily about providing context rather than performing actions, resources are usually the better primitive.&lt;/p&gt;</description></item><item><title>Roadmap</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/development/roadmap/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/development/roadmap/</guid><description>Our plans for evolving Model Context Protocol</description></item><item><title>Roots</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/client/roots/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/client/roots/</guid><description/></item><item><title>Sampling</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/client/sampling/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/client/sampling/</guid><description>&lt;p&gt;Sampling is the mechanism that allows an MCP server to request LLM completions through the client, effectively enabling servers to leverage AI capabilities without embedding their own model access. This is one of the most powerful and least intuitive parts of the MCP specification because it inverts the typical client-server relationship. Pay careful attention to the human-in-the-loop requirements, since the spec mandates that clients must obtain user approval before fulfilling sampling requests, which has significant UX implications. If you are building agentic MCP servers that need to reason or generate text, understanding this capability is essential.&lt;/p&gt;</description></item><item><title>Schema Reference</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/schema/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/schema/</guid><description/></item><item><title>SDK Tiering System</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/sdk-tiers/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/sdk-tiers/</guid><description>Feature completeness, protocol support, and maintenance commitment levels for Model Context Protocol SDKs</description></item><item><title>SDKs</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/sdk/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/sdk/</guid><description>Official SDKs for building with Model Context Protocol</description></item><item><title>Security Best Practices</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/tutorials/security/security_best_practices/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/tutorials/security/security_best_practices/</guid><description>Security considerations, attack vectors, and best practices for MCP implementations</description></item><item><title>SEP Guidelines</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/sep-guidelines/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/sep-guidelines/</guid><description>Specification Enhancement Proposal (SEP) guidelines for proposing changes to the Model Context Protocol</description></item><item><title>SEP-1024: MCP Client Security Requirements for Local Server Installation</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1024-mcp-client-security-requirements-for-local-server-/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1024-mcp-client-security-requirements-for-local-server-/</guid><description>MCP Client Security Requirements for Local Server Installation</description></item><item><title>SEP-1024: MCP Client Security Requirements for Local Server Installation</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1024-mcp-client-security-requirements-for-local-server-/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1024-mcp-client-security-requirements-for-local-server-/</guid><description>MCP Client Security Requirements for Local Server Installation</description></item><item><title>SEP-1034: Support default values for all primitive types in elicitation schemas</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1034--support-default-values-for-all-primitive-types-in/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1034--support-default-values-for-all-primitive-types-in/</guid><description>Support default values for all primitive types in elicitation schemas</description></item><item><title>SEP-1034: Support default values for all primitive types in elicitation schemas</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1034--support-default-values-for-all-primitive-types-in/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1034--support-default-values-for-all-primitive-types-in/</guid><description>Support default values for all primitive types in elicitation schemas</description></item><item><title>SEP-1036: URL Mode Elicitation for secure out-of-band interactions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1036-url-mode-elicitation-for-secure-out-of-band-intera/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1036-url-mode-elicitation-for-secure-out-of-band-intera/</guid><description>URL Mode Elicitation for secure out-of-band interactions</description></item><item><title>SEP-1036: URL Mode Elicitation for secure out-of-band interactions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1036-url-mode-elicitation-for-secure-out-of-band-intera/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1036-url-mode-elicitation-for-secure-out-of-band-intera/</guid><description>URL Mode Elicitation for secure out-of-band interactions</description></item><item><title>SEP-1046: Support OAuth client credentials flow in authorization</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1046-support-oauth-client-credentials-flow-in-authoriza/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1046-support-oauth-client-credentials-flow-in-authoriza/</guid><description>Support OAuth client credentials flow in authorization</description></item><item><title>SEP-1046: Support OAuth client credentials flow in authorization</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1046-support-oauth-client-credentials-flow-in-authoriza/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1046-support-oauth-client-credentials-flow-in-authoriza/</guid><description>Support OAuth client credentials flow in authorization</description></item><item><title>SEP-1302: Formalize Working Groups and Interest Groups in MCP Governance</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1302-formalize-working-groups-and-interest-groups-in-mc/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1302-formalize-working-groups-and-interest-groups-in-mc/</guid><description>Formalize Working Groups and Interest Groups in MCP Governance</description></item><item><title>SEP-1302: Formalize Working Groups and Interest Groups in MCP Governance</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1302-formalize-working-groups-and-interest-groups-in-mc/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1302-formalize-working-groups-and-interest-groups-in-mc/</guid><description>Formalize Working Groups and Interest Groups in MCP Governance</description></item><item><title>SEP-1303: Input Validation Errors as Tool Execution Errors</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1303-input-validation-errors-as-tool-execution-errors/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1303-input-validation-errors-as-tool-execution-errors/</guid><description>Input Validation Errors as Tool Execution Errors</description></item><item><title>SEP-1303: Input Validation Errors as Tool Execution Errors</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1303-input-validation-errors-as-tool-execution-errors/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1303-input-validation-errors-as-tool-execution-errors/</guid><description>Input Validation Errors as Tool Execution Errors</description></item><item><title>SEP-1319: Decouple Request Payload from RPC Methods Definition</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1319-decouple-request-payload-from-rpc-methods-definiti/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1319-decouple-request-payload-from-rpc-methods-definiti/</guid><description>Decouple Request Payload from RPC Methods Definition</description></item><item><title>SEP-1319: Decouple Request Payload from RPC Methods Definition</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1319-decouple-request-payload-from-rpc-methods-definiti/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1319-decouple-request-payload-from-rpc-methods-definiti/</guid><description>Decouple Request Payload from RPC Methods Definition</description></item><item><title>SEP-1330: Elicitation Enum Schema Improvements and Standards Compliance</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1330-elicitation-enum-schema-improvements-and-standards/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1330-elicitation-enum-schema-improvements-and-standards/</guid><description>Elicitation Enum Schema Improvements and Standards Compliance</description></item><item><title>SEP-1330: Elicitation Enum Schema Improvements and Standards Compliance</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1330-elicitation-enum-schema-improvements-and-standards/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1330-elicitation-enum-schema-improvements-and-standards/</guid><description>Elicitation Enum Schema Improvements and Standards Compliance</description></item><item><title>SEP-1577: Sampling With Tools</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1577--sampling-with-tools/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1577--sampling-with-tools/</guid><description>Sampling With Tools</description></item><item><title>SEP-1577: Sampling With Tools</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1577--sampling-with-tools/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1577--sampling-with-tools/</guid><description>Sampling With Tools</description></item><item><title>SEP-1613: Establish JSON Schema 2020-12 as Default Dialect for MCP</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1613-establish-json-schema-2020-12-as-default-dialect-f/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1613-establish-json-schema-2020-12-as-default-dialect-f/</guid><description>Establish JSON Schema 2020-12 as Default Dialect for MCP</description></item><item><title>SEP-1613: Establish JSON Schema 2020-12 as Default Dialect for MCP</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1613-establish-json-schema-2020-12-as-default-dialect-f/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1613-establish-json-schema-2020-12-as-default-dialect-f/</guid><description>Establish JSON Schema 2020-12 as Default Dialect for MCP</description></item><item><title>SEP-1686: Tasks</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1686-tasks/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1686-tasks/</guid><description>Tasks</description></item><item><title>SEP-1686: Tasks</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1686-tasks/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1686-tasks/</guid><description>Tasks</description></item><item><title>SEP-1699: Support SSE polling via server-side disconnect</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1699-support-sse-polling-via-server-side-disconnect/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1699-support-sse-polling-via-server-side-disconnect/</guid><description>Support SSE polling via server-side disconnect</description></item><item><title>SEP-1699: Support SSE polling via server-side disconnect</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1699-support-sse-polling-via-server-side-disconnect/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1699-support-sse-polling-via-server-side-disconnect/</guid><description>Support SSE polling via server-side disconnect</description></item><item><title>SEP-1730: SDKs Tiering System</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1730-sdks-tiering-system/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1730-sdks-tiering-system/</guid><description>SDKs Tiering System</description></item><item><title>SEP-1730: SDKs Tiering System</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1730-sdks-tiering-system/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1730-sdks-tiering-system/</guid><description>SDKs Tiering System</description></item><item><title>SEP-1850: PR-Based SEP Workflow</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1850-pr-based-sep-workflow/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1850-pr-based-sep-workflow/</guid><description>PR-Based SEP Workflow</description></item><item><title>SEP-1850: PR-Based SEP Workflow</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1850-pr-based-sep-workflow/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1850-pr-based-sep-workflow/</guid><description>PR-Based SEP Workflow</description></item><item><title>SEP-1865: MCP Apps - Interactive User Interfaces for MCP</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1865-mcp-apps-interactive-user-interfaces-for-mcp/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/1865-mcp-apps-interactive-user-interfaces-for-mcp/</guid><description>MCP Apps - Interactive User Interfaces for MCP</description></item><item><title>SEP-1865: MCP Apps - Interactive User Interfaces for MCP</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1865-mcp-apps-interactive-user-interfaces-for-mcp/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/1865-mcp-apps-interactive-user-interfaces-for-mcp/</guid><description>MCP Apps - Interactive User Interfaces for MCP</description></item><item><title>SEP-2085: Governance Succession and Amendment Procedures</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/2085-governance-succession-and-amendment/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/2085-governance-succession-and-amendment/</guid><description>Governance Succession and Amendment Procedures</description></item><item><title>SEP-2085: Governance Succession and Amendment Procedures</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2085-governance-succession-and-amendment/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2085-governance-succession-and-amendment/</guid><description>Governance Succession and Amendment Procedures</description></item><item><title>SEP-2133: Extensions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/2133-extensions/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/2133-extensions/</guid><description>Extensions</description></item><item><title>SEP-2133: Extensions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2133-extensions/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2133-extensions/</guid><description>Extensions</description></item><item><title>SEP-2148: MCP Contributor Ladder</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2148-contributor-ladder/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2148-contributor-ladder/</guid><description>MCP Contributor Ladder</description></item><item><title>SEP-2149: MCP Group Governance and Charter Template</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2149-working-group-charter-template/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2149-working-group-charter-template/</guid><description>MCP Group Governance and Charter Template</description></item><item><title>SEP-2207: OIDC-Flavored Refresh Token Guidance</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2207-oidc-refresh-token-guidance/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2207-oidc-refresh-token-guidance/</guid><description>OIDC-Flavored Refresh Token Guidance</description></item><item><title>SEP-2260: Require Server requests to be associated with a Client request.</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2260-require-server-requests-to-be-associated-with-client-requests/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/2260-require-server-requests-to-be-associated-with-client-requests/</guid><description>Require Server requests to be associated with a Client request.</description></item><item><title>SEP-414: Document OpenTelemetry Trace Context Propagation Conventions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/414-request-meta/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/414-request-meta/</guid><description>Document OpenTelemetry Trace Context Propagation Conventions</description></item><item><title>SEP-414: Document OpenTelemetry Trace Context Propagation Conventions</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/414-request-meta/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/414-request-meta/</guid><description>Document OpenTelemetry Trace Context Propagation Conventions</description></item><item><title>SEP-932: Model Context Protocol Governance</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/932-model-context-protocol-governance/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/932-model-context-protocol-governance/</guid><description>Model Context Protocol Governance</description></item><item><title>SEP-932: Model Context Protocol Governance</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/932-model-context-protocol-governance/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/932-model-context-protocol-governance/</guid><description>Model Context Protocol Governance</description></item><item><title>SEP-973: Expose additional metadata for Implementations, Resources, Tools and Prompts</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/973-expose-additional-metadata-for-implementations-res/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/973-expose-additional-metadata-for-implementations-res/</guid><description>Expose additional metadata for Implementations, Resources, Tools and Prompts</description></item><item><title>SEP-973: Expose additional metadata for Implementations, Resources, Tools and Prompts</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/973-expose-additional-metadata-for-implementations-res/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/973-expose-additional-metadata-for-implementations-res/</guid><description>Expose additional metadata for Implementations, Resources, Tools and Prompts</description></item><item><title>SEP-985: Align OAuth 2.0 Protected Resource Metadata with RFC 9728</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/985-align-oauth-20-protected-resource-metadata-with-rf/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/985-align-oauth-20-protected-resource-metadata-with-rf/</guid><description>Align OAuth 2.0 Protected Resource Metadata with RFC 9728</description></item><item><title>SEP-985: Align OAuth 2.0 Protected Resource Metadata with RFC 9728</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/985-align-oauth-20-protected-resource-metadata-with-rf/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/985-align-oauth-20-protected-resource-metadata-with-rf/</guid><description>Align OAuth 2.0 Protected Resource Metadata with RFC 9728</description></item><item><title>SEP-986: Specify Format for Tool Names</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/986-specify-format-for-tool-names/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/986-specify-format-for-tool-names/</guid><description>Specify Format for Tool Names</description></item><item><title>SEP-986: Specify Format for Tool Names</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/986-specify-format-for-tool-names/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/986-specify-format-for-tool-names/</guid><description>Specify Format for Tool Names</description></item><item><title>SEP-990: Enable enterprise IdP policy controls during MCP OAuth flows</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/990-enable-enterprise-idp-policy-controls-during-mcp-o/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/990-enable-enterprise-idp-policy-controls-during-mcp-o/</guid><description>Enable enterprise IdP policy controls during MCP OAuth flows</description></item><item><title>SEP-990: Enable enterprise IdP policy controls during MCP OAuth flows</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/990-enable-enterprise-idp-policy-controls-during-mcp-o/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/990-enable-enterprise-idp-policy-controls-during-mcp-o/</guid><description>Enable enterprise IdP policy controls during MCP OAuth flows</description></item><item><title>SEP-991: Enable URL-based Client Registration using OAuth Client ID Metadata Documents</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/991-enable-url-based-client-registration-using-oauth-c/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/991-enable-url-based-client-registration-using-oauth-c/</guid><description>Enable URL-based Client Registration using OAuth Client ID Metadata Documents</description></item><item><title>SEP-991: Enable URL-based Client Registration using OAuth Client ID Metadata Documents</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/991-enable-url-based-client-registration-using-oauth-c/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/991-enable-url-based-client-registration-using-oauth-c/</guid><description>Enable URL-based Client Registration using OAuth Client ID Metadata Documents</description></item><item><title>SEP-994: Shared Communication Practices/Guidelines</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/994-shared-communication-practicesguidelines/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/994-shared-communication-practicesguidelines/</guid><description>Shared Communication Practices/Guidelines</description></item><item><title>SEP-994: Shared Communication Practices/Guidelines</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/994-shared-communication-practicesguidelines/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/994-shared-communication-practicesguidelines/</guid><description>Shared Communication Practices/Guidelines</description></item><item><title>Server Card Charter</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/server-card/charter/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/server-card/charter/</guid><description>Charter for the MCP Server Card Working Group.</description></item><item><title>Specification</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/_overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/_overview/</guid><description/></item><item><title>Specification Enhancement Proposals (SEPs)</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/_overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/seps/_overview/</guid><description>Index of all MCP Specification Enhancement Proposals</description></item><item><title>Specification Enhancement Proposals (SEPs)</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/_overview/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/seps/_overview/</guid><description>Index of all MCP Specification Enhancement Proposals</description></item><item><title>Tasks</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/utilities/tasks/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/utilities/tasks/</guid><description/></item><item><title>The MCP Registry</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/about/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/about/</guid><description>&lt;p&gt;This is the starting point for understanding the MCP registry, the centralized discovery layer that lets host applications find and install MCP servers by name. The registry is what turns MCP from a protocol into an ecosystem, so grasping its design goals and trust model is important before publishing or consuming servers. Read this overview first, then move to authentication and package types for the operational details. If you are evaluating whether to publish your MCP server publicly or keep it private, this page covers the discoverability and governance tradeoffs.&lt;/p&gt;</description></item><item><title>The MCP Registry Moderation Policy</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/moderation-policy/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/moderation-policy/</guid><description/></item><item><title>Tools</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/tools/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/server/tools/</guid><description>&lt;p&gt;Tools are the most commonly used MCP primitive &amp;ndash; they let the model invoke server-side functions with structured inputs and receive results. Focus on the JSON Schema-based input validation, which is how the model knows what arguments a tool accepts. A critical detail is that tool calls are model-initiated but require human approval in most host implementations, so design your tool descriptions to be clear enough that users understand what they are approving. Keep tool names concise and descriptions precise, as the model relies heavily on them for deciding when and how to call each tool.&lt;/p&gt;</description></item><item><title>Transports</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/transports/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/2025-11-25/basic/transports/</guid><description>&lt;p&gt;MCP defines two transport mechanisms: stdio (standard input/output) and HTTP with Server-Sent Events (SSE). For local development and CLI-based servers, stdio is simpler and the right default choice. HTTP+SSE is needed when the server runs remotely or must handle multiple clients. A common gotcha is that the Streamable HTTP transport replaced the older SSE-only transport in the 2025-11-25 spec revision, so be careful not to follow outdated examples that use the previous approach.&lt;/p&gt;</description></item><item><title>Triggers and Events Charter</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/triggers-events/charter/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/triggers-events/charter/</guid><description>Charter for the MCP Triggers and Events Working Group.</description></item><item><title>Understanding Authorization in MCP</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/tutorials/security/authorization/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/tutorials/security/authorization/</guid><description>Learn how to implement secure authorization for MCP servers using OAuth 2.1 to protect sensitive resources and operations</description></item><item><title>Understanding MCP clients</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/learn/client-concepts/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/learn/client-concepts/</guid><description>&lt;p&gt;Most developers will build servers rather than clients, but understanding the client side is critical for grasping the full protocol flow. The key insight is that the client acts as a gatekeeper: it decides which server capabilities to expose to the model and enforces security boundaries. Pay attention to how capability negotiation works during initialization, since both sides must agree on what features they support before any real work happens.&lt;/p&gt;</description></item><item><title>Understanding MCP servers</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/learn/server-concepts/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/learn/server-concepts/</guid><description>&lt;p&gt;This page explains the three core primitives that MCP servers expose: Tools, Resources, and Prompts. Focus on understanding when to use each one &amp;ndash; Tools let the model take actions, Resources provide read-only data the model can pull in, and Prompts are reusable templates for common interactions. A frequent mistake is implementing everything as a tool when a resource would be more appropriate and give the host application more control over how data is presented to the model.&lt;/p&gt;</description></item><item><title>Versioning</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/versioning/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/specification/versioning/</guid><description/></item><item><title>Versioning Published MCP Servers</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/versioning/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/registry/versioning/</guid><description>&lt;p&gt;Getting versioning right is essential for MCP server publishers because clients may pin to specific versions, and breaking changes without a major version bump will silently break downstream integrations. Pay close attention to how semantic versioning interacts with registry resolution rules and what happens when you publish a version that a client cannot upgrade to automatically. If you maintain servers consumed by multiple host applications, read this alongside the package types guide to understand how versioning constraints differ across package formats.&lt;/p&gt;</description></item><item><title>What is the Model Context Protocol (MCP)?</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/getting-started/intro/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/docs/getting-started/intro/</guid><description>&lt;p&gt;This is the single best starting point for understanding MCP. Focus on the core value proposition: MCP standardizes how AI applications connect to external data and tools, replacing fragile one-off integrations with a shared protocol. Pay attention to the analogy with USB-C — MCP aims to be a universal connector between LLMs and the systems they need to interact with. The original page also covers building MCP Apps — interactive apps that run inside AI clients — via the &lt;a href="https://modelcontextprotocol.io/extensions/apps/overview"&gt;MCP Apps overview&lt;/a&gt;. Read this before diving into architecture or specification pages.&lt;/p&gt;</description></item><item><title>Working and Interest Groups</title><link>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/working-interest-groups/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/mcp/community/working-interest-groups/</guid><description>Learn about the two forms of collaborative groups within the Model Context Protocol&amp;rsquo;s governance structure - Working Groups and Interest Groups.</description></item></channel></rss>