llmcontext
The self-hosted context layer for AI agents. Index private repos, internal packages, and every pinned dependency inside your own infrastructure, and serve grounded, version-pinned context to any MCP agent.
https://llmcontext.dev/Opens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://mcp.llmcontext.dev/We add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · mcp.llmcontext.dev
3tools discovered
Get Context
An evidence concierge for the coding agent. It finds and summarizes information from ONE exact package version; it does not implement the change. The executor coding agent remains responsible for interpreting the evidence, fitting it to the local codebase, editing code, and validating the result. Evidence is grounded in indexed source and documentation rather than training data — which drifts, and which you cannot audit from the inside. Call search_packages first, then pass its exact package na
Code Graph
Structural lookups over a package's call graph: what reaches a symbol, what it reaches, and where it is defined. Answers questions about how code is CONNECTED, which is the one thing get_context cannot do — semantic search finds text that reads like your query, not the callee three files away whose body is the actual implementation. CALL THIS when: • You are about to change a function and need its blast radius — relation="impact". • You have found a symbol and need the code that actually im
Search Packages
Discover indexed packages, look up available versions, or triage whether a package has a specific feature — without fetching full chunk content. This is the step for when you do not know what is out there. If the project's lock file already pins a version, skip this and call get_context with that version directly. Use for: • Version lookup: "what versions of fastapi are indexed" → returns all indexed versions • Discovery: "library for HTTP retry with backoff in Python" → surfaces relevant
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsThe self-hosted context layer for AI agents. Index private repos, internal packages, and every pinned dependency inside your own infrastructure, and serve grounded, version-pinned context to any MCP agent.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
MCPBundles probed 3 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Operate llmcontext? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.