The shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.
The shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.
Think of it as an X-ray of your repo that your agent can read: one structure that combines everything and says where each thing lives, what that program is for, what is being worked on, what is done and what is still open. That panorama is the thing no other tool hands your agent.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"m1nd": {
"command": "npx",
"args": ["-y", "@maxkle1nz/m1nd"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
GitHub CI/CD MCP server with 70 tools for repos, PRs, Actions, deployments, billing, and more.
This repository provides a set of utilities to build an MCP server (Model Context Protocol) that you can integrate with your conversational AI client.
Chrome breakpoint debugging MCP server for inspecting runtime values and stepping through code
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud