What tools does Revit API MCP provide?
Four tools: `search-docs` (search documentation), `retrieve-doc` (get one doc page), `retrieve-docs` (get multiple doc pages from a query), and `search-library` (semantic search over learning resources).
@kaitpw
基本情報
Give LLMs the power of direct access to the Revit API docs and related content (from The Building Coder blog) via an MCP server.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"revit-api-docs (with search-library enabled)": {
"command": "path\\to\\Rvt_Docs_MCP-windows.exe -k 'sk-xxx' -v 'vs_xxx'"
},
"revit-api-docs (macos-arm64)": {
"command": "path/to/Rvt_Docs_MCP-macos-arm64"
},
"revit-api-docs (macos-x64)": {
"command": "path/to/Rvt_Docs_MCP-macos-x64"
},
"revit-api-docs (windows)": {
"command": "path\\to\\Rvt_Docs_MCP-windows.exe"
}
}
}Search Revit API documentation to find entities matching
Retrieve a single Revit API documentation page using its
Get full documentation content for multiple Revit API
Search a comprehensive library of Revit API learning
Revit API MCP is a Model Context Protocol server that provides tools for searching and retrieving Autodesk Revit API documentation. It also offers a semantic search over a curated library of Revit API learning resources, including blog posts, code examples, and practical guides. It is intended for developers working with the Revit API who need quick access to documentation and educational material.
Download the executable for your operating system from the GitHub Releases page, then add its path to your MCP client’s configuration under mcpServers. The configuration key should match your OS (e.g., revit-api-docs (windows)). To enable the search-library tool, you must also run the executable with the -k (OpenAI API key) and -v (OpenAI vector store ID) flags.
Four tools: `search-docs` (search documentation), `retrieve-doc` (get one doc page), `retrieve-docs` (get multiple doc pages from a query), and `search-library` (semantic search over learning resources).
First, follow the steps in the [Rvt_Docs_Tbc_Embedder](https://github.com/kaitpw/Rvt_Docs_TBC_Embedder) repository to create an OpenAI vector store. Then run the executable with the `-k` flag for your OpenAI API key and the `-v` flag for your vector store ID.
Precompiled executables for Windows, macOS (arm64 and x64) are available on the [GitHub Releases page](https://github.com/kaitpw/Rvt_Docs_MCP/releases). You can also build from source using `deno task compile`.
No additional runtime is needed if you use the precompiled executable. The `search-library` feature requires an OpenAI API key and a vector store ID, but no other dependencies.
The server itself does not require authentication. For the `search-library` tool, you must provide an OpenAI API key and a vector store ID as command‑line flags.

Model Context Protocol Servers

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
コメント