Skip to content
Back to search

claude-ai-mcp

MCP serverOfficial: AnthropicGitHub

Report issues related to MCP integration with Claude here.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/anthropics--claude-ai-mcp/badge.svg)](/listings/anthropics--claude-ai-mcp)

HTML

<a href="/listings/anthropics--claude-ai-mcp"><img src="/api/listings/anthropics--claude-ai-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 45 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Claude.ai MCP Integration
  2. This repository is the communication hub for **MCP (Model Context Protocol) integration in Claude.ai**. Use it to stay updated on technical changes and to report bugs or request features.
  3. ## How to Stay Updated
  4. **For announcements only** (low noise):
  5. 1. Go to [Discussions](../../discussions)
  6. 2. Select the Announcements category, go to any message in the list, then click **Subscribe**
  7. You'll be notified of:
  8. - Protocol changes (SSE deprecation, Streamable HTTP updates)
  9. - Session behavior changes
  10. - New MCP capabilities
  11. - Breaking changes and deprecations
  12. - Security updates
  13. ## Report a Bug or Request a Feature
  14. Use [Issues](../../issues/new/choose) to:
  15. - Report bugs with MCP servers or integrations
  16. - Request new features or improvements
  17. ## What This Covers
  18. - **Integrations** - Connecting MCP servers to Claude.ai
  19. - **Session Management** - Initialization, reconnection, and lifecycle behavior
  20. - **Protocol Support** - SSE, Streamable HTTP, transport changes
  21. - **Tool & Resource Handling** - How Claude.ai discovers and invokes MCP tools
  22. - **OAuth & Authentication** - Token handling for MCP servers
  23. ## What This Does NOT Cover
  24. - The MCP specification itself → [modelcontextprotocol/specification](https://github.com/modelcontextprotocol/specification)
  25. - MCP SDKs → [modelcontextprotocol](https://github.com/modelcontextprotocol)
  26. - General Claude.ai issues (non-MCP) → [support.anthropic.com](https://support.anthropic.com)
  27. ## Resources
  28. - [MCP Specification](https://spec.modelcontextprotocol.io)
  29. - [MCP Directory](https://www.claudemcp.com)
  30. ## License
  31. Use is subject to [Anthropic's Commercial Terms of Service](https://www.anthropic.com/legal/commercial-terms).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.