About llmref
llmref is a Claude Code plugin connecting to a versioned documentation registry and semantic search service, for agents looking up model-ready documentation. It also includes a skill that guides agents on when and how to use the lookup tools.
Key features
- 01List projects and documentation versions
- 02Resolve documentation for a selected version
- 03Search documentation semantically
- 04Optionally report missing documentation
- 05Include an agent skill for tool-use guidance
Use cases
- 01Find documentation for a specific library version
- 02Verify API usage against docs rather than training data
- 03Guide an agent's research in Claude Code
- 04Report missing public documentation to the registry
MCP support
It connects to a remote MCP server exposing project and version listings, documentation resolution, semantic search, and optional missing-documentation feedback tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.llmref.org/v1/mcpclaude mcp add --transport http org-llmref-llmref https://api.llmref.org/v1/mcp{"mcpServers":{"org-llmref-llmref":{"type":"http","url":"https://api.llmref.org/v1/mcp"}}}Open in Cursor{"servers":{"org-llmref-llmref":{"type":"http","url":"https://api.llmref.org/v1/mcp"}}}Open in VS Code{"mcpServers":{"org-llmref-llmref":{"type":"http","url":"https://api.llmref.org/v1/mcp"}}}{"mcpServers":{"org-llmref-llmref":{"serverUrl":"https://api.llmref.org/v1/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
4| Parameter | Type | Required | Description |
|---|---|---|---|
| skip | integer|null | No | Number of results to skip, for pagination (default 0). |
| limit | integer|null | No | Maximum number of results to return (default 50, max 200). |
| query | string|null | No | Forgiving fuzzy filter over project slugs; results are ranked by relevance. |
Details
From the project READMELLM Reference plugin
A Claude Code plugin that connects to LLM Reference - versioned, model-ready documentation and semantic search - and ships a skill that teaches an agent how and when to use it.
What you get
- MCP server
llmref(remote,https://api.llmref.org/v1/mcp) exposinglist_projects,list_versions,resolve_docs,search_docs, and the optionalreport_missing_docsfeedback method. - Skill
llmrefthat tells the agent to prefer LLM Reference over training data for version-specific docs, and the order to call the tools in.
Install (Claude Code)
/plugin marketplace add reclear-io/llmref-plugin
/plugin install llmref@llmref
Use in any other MCP client
The server is a plain remote streamable-HTTP MCP endpoint, so any MCP-capable client can connect directly:
https://api.llmref.org/v1/mcp
Per-client setup (Claude Desktop, Cursor, Codex, and others) is documented at https://llmref.org.
License
MIT - Open Source by Reclear.io
Optional discovery feedback
When permitted, the skill quietly reports missing public docs and any official llms.txt or docs URL already found during the task. It never waits for ingestion or sends conversation text, code, credentials or private URLs. Tell the agent not to report to opt out. Host permissions apply. See PRIVACY.md.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.