The Model Context Protocol (MCP) is an open protocol that enables seamless integration between [LLM](/pages/Large%20language%20model.txt) applications and external data sources and tools. Whether you're building an AI-powered [IDE](/pages/Integrated%20development%20environment.txt), enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

## Articles

- 2025-05-30 - [Poison everywhere: No output from your MCP server is safe](https://www.cyberark.com/resources/threat-research-blog/poison-everywhere-no-output-from-your-mcp-server-is-safe)
- <2025-04-15> - [Everything Wrong with MCP - by Shrivu Shankar](https://blog.sshh.io/p/everything-wrong-with-mcp)
- [Introduction - Model Context Protocol](https://modelcontextprotocol.io/introduction)

## MCP servers

- [Awesome MCP Servers - A curated list of Model Context Protocol servers](https://github.com/appcypher/awesome-mcp-servers)

## See also

- [Agent-computer interaction](/pages/Agent-computer%20interaction.txt)
- [MCP Run Python](/pages/MCP%20Run%20Python.txt)