Revit API MCP

What is Revit API MCP?

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.

How to use Revit API MCP?

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.

Key features of Revit API MCP

• Search Revit API documentation for matching entities.
• Retrieve a single documentation page using its URL slug.
• Retrieve full documentation for multiple entities from a query.
• Search a library of Revit API learning resources using semantic search.

Use cases of Revit API MCP

• Quickly finding a Revit API class or method by name or description.
• Getting the full documentation for a specific API entity without opening a browser.
• Collecting documentation for several related API elements at once.
• Discovering blog posts, code examples, and guides relevant to a Revit API topic.

FAQ from Revit API MCP

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).

How do I enable the search-library tool?

First, follow the steps in the 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.

Where can I download Revit API MCP?

Precompiled executables for Windows, macOS (arm64 and x64) are available on the GitHub Releases page. You can also build from source using deno task compile.

What runtime or dependencies are required?

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.

How is authentication handled?

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.