MCP-Server-IETF
@tizee
A Model Context Protocol server for fetching IETF documents (RFCs) for Large Language Models.
Overview
What is MCP-Server-IETF?
A Model Context Protocol server that provides access to IETF RFC documents for Large Language Models. It downloads and caches the RFC index and documents, enabling LLMs to retrieve specifications through a standardized interface.
How to use MCP-Server-IETF?
Install from source with pip install -e . and start the server using the command mcp-server-ietf. Alternatively, use it with the MCP inspector via npx @modelcontextprotocol/inspector uv run mcp-server-ietf. Tools include list_docs_number (get total RFC count), get_doc (fetch an RFC by number with line-based pagination), and search_rfc_by_keyword (search by keyword in titles).
Key features of MCP-Server-IETF
- Downloads and caches the RFC index and documents.
- Search RFCs by keyword in titles.
- Access RFC documents with line-based pagination.
- Extracts metadata like page numbers from documents.
Use cases of MCP-Server-IETF
—
FAQ from MCP-Server-IETF
What are the runtime requirements?
Python 3.11 or higher is required, along with dependencies listed in pyproject.toml.
Where are cached documents stored?
The default cache directory is ~/.cache/ietf-doc-server.
What environment variables are available?
LOG_LEVEL can be set to control logging verbosity (default: "DEBUG").
How do I interact with the server?
After starting the server, three tools are exposed: list_docs_number, get_doc, and search_rfc_by_keyword. Example: get_doc accepts parameters number, start_line, and max_lines.
What license does it use?
MIT License, as stated in the LICENSE file.
