MCP-Server-IETF
Provides integration with Git for cloning the repository during installation from source.
Enables accessing the source repository at github.com/tizee/mcp-server-ietf for installation and contributions.
Supports development workflows through a Makefile with commands for running the inspector and tests.
Integrates with pytest for running the test suite to validate server functionality.
Built on Python 3.11+, utilizing its capabilities for implementing the MCP server functionality.
Uses TOML format for dependency management through the pyproject.toml file.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP-Server-IETF search for RFCs about HTTP protocol"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP-Server-IETF
A Model Context Protocol server for fetching IETF documents (RFCs) for Large Language Models.
Overview
This project implements a Model Context Protocol (MCP) server that provides access to IETF RFC documents. It enables Large Language Models to access RFC specifications through a standardized interface.
Key features:
Download and cache RFC index and documents
Search RFCs by keyword in titles
Access RFC documents with pagination support
Extract metadata like page numbers from documents
Related MCP server: Unstructured Document Processor MCP
Installation
Requirements
Python 3.11 or higher
Dependencies as listed in
pyproject.toml
Install from source
# Clone the repository
git clone https://github.com/tizee/mcp-server-ietf
cd mcp-server-ietf
# Install with pip
pip install -e .Usage
Starting the server
# Start the server
mcp-server-ietfOr use it with the MCP inspector:
npx @modelcontextprotocol/inspector uv run mcp-server-ietfAvailable Tools
When connected to the server, the following tools are available:
list_docs_number
Get the total number of RFC documents available in the index.
get_doc
Get an RFC document by its number with pagination support.
Parameters:
number: The RFC number (e.g., "1234")start_line: The line number to start from (default: 1)max_lines: Maximum number of lines to return (default: 200)
search_rfc_by_keyword
Search for RFC documents by keyword in their titles.
Parameters:
keyword: The search term to look for in RFC titles
Development
Setup Development Environment
# Install development dependencies
uv install -e .[dev]Run inspector with Makefile:
make devRunning Tests
# Run tests
uv run pytestOr using the Makefile:
make testCache Location
By default, the server caches RFC documents and the index at ~/.cache/ietf-doc-server.
Environment Variables
LOG_LEVEL: Set the logging level (default: "DEBUG")
License
MIT License - See LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Available Tools
3 toolsget_ietf_docC
Get an RFC document by its number in RFC editor Index with pagination support
Args:
number: The RFC number str (e.g., "1234")
start_line: The line number to start from (default: 1)
max_lines: Maximum number of lines to return (default: 200)
Returns:
A dictionary containing the document content and metadata
Inputs: number (required), max_lines, start_line.
list_ietf_docs_numberB
Get the total number of IETF RFC documents available in RFC editor Index
Inputs: no named parameters.
search_ietf_rfc_by_keywordB
Search for IETF RFC documents from RFC Editor Index by keyword in their titles
Args:
keyword: The keyword to search for
Returns:
A list of matching RFCs with their numbers and titles
Inputs: keyword (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose with no overlap: get_ietf_doc retrieves specific documents, list_ietf_docs_number provides metadata about document count, and search_ietf_rfc_by_keyword enables keyword-based discovery. The descriptions clearly differentiate between retrieval, counting, and searching functions.
The tools follow a mostly consistent verb_noun pattern with get_, list_, and search_ prefixes, though 'list_ietf_docs_number' deviates slightly by including 'number' in the name rather than using a more conventional pattern like 'count_ietf_docs'. The snake_case convention is consistently applied throughout.
With only 3 tools, the server feels somewhat thin for an IETF/RFC document access service. While the tools cover basic retrieval and search, the count is borderline minimal for what could reasonably include operations like filtering by date, accessing drafts, or managing document collections.
The toolset covers fundamental document access (get, count, search) but has notable gaps for a complete IETF document service. Missing operations include filtering by date or status, accessing IETF drafts (not just RFCs), and more advanced search capabilities beyond simple keyword matching in titles.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server enabling LLMs to search, retrieve, and manage documents through Rememberizer's knowledge management API.36Apache 2.0
- FlicenseBqualityDmaintenanceA Model Context Protocol server that enables LLMs to extract and use content from unstructured documents across a wide variety of file formats.111-
- AlicenseBqualityDmaintenanceA Model Context Protocol (MCP) compliant server that allows Large Language Models (LLMs) to search and retrieve content from microCMS APIs.2MIT
- FlicenseNot gradedqualityDmaintenanceA simple Model Context Protocol server that enables searching and retrieving relevant documentation snippets from Langchain, Llama Index, and OpenAI official documentation.-