Fep MCP
This is an MCP server for accessing Federal Universe Enhancement Proposal (FEP) documents. By cloning the FEP code repository and exposing tools and resources, it enables AI assistants to read and search FEP documents, solving the access restriction problem caused by Codeberg's anti - AI protection.
2.5 points
4.6K

What is the FEP MCP Server?

The FEP MCP server is a tool specifically designed for AI assistants, which can access and search Federal Universe Enhancement Proposal (FEP) documents. FEPs are proposal documents similar to Internet RFCs, used to improve the functionality and interoperability of the Fediverse platforms. Since FEP documents are hosted on the Codeberg platform, which has protection measures to prevent direct scraping by AI tools, this MCP server solves this problem by cloning the repository locally.

How to use the FEP MCP Server?

You can configure the FEP MCP server in an AI assistant client that supports the MCP protocol, such as Claude Desktop or Claude Code. After configuration, the AI assistant can access FEP documents through this server, including listing all FEPs, searching for specific content, and obtaining detailed documents. The server will automatically clone the latest FEP repository when it starts to ensure the timeliness of the documents.

Applicable Scenarios

The FEP MCP server is very useful when you need an AI assistant to help understand the technical specifications of the Fediverse, find specific FEP proposals, learn about the technical implementation details of a certain function, or study the development direction of Fediverse platforms. It is particularly suitable for developers, technical researchers, and users interested in Fediverse technology.

Main Features

List FEP Proposals
It can list all available FEP proposals and support filtering by status (draft, final, withdrawn). Each proposal contains metadata information such as title, author, and status.
Get a Specific FEP
Obtain the complete content of an FEP document through a 4 - digit hexadecimal identifier (e.g., a4ed). The document is provided in Markdown format for easy reading and parsing.
Search FEP Content
Perform a full - text search in the titles, authors, and content of FEP documents to help quickly find relevant technical proposals.
Update the Document Library
Manually trigger the operation of pulling the latest FEP documents from the remote repository to ensure that the latest proposal content is obtained.
Resource Access
Access FEP content through a unified resource URI (e.g., fep://index to get the index, fep://{slug} to get a specific document), providing a standardized access interface.
Advantages
Bypass access restrictions: Solve the direct access restrictions for AI tools on the Codeberg platform
Local cache: Documents are cached locally, with fast access speed and reduced network latency
Standardized interface: Provide a unified and standardized access method through the MCP protocol
Easy to integrate: Can be easily integrated into AI assistant clients that support MCP
Complete documents: Provide a complete collection of FEP documents, including metadata and content
Limitations
Manual update required: Documents are not automatically updated in real - time and need to be manually refreshed or the service needs to be restarted
Dependent on the Deno environment: Requires the Deno runtime environment and corresponding permissions to run
Limited to FEP documents: The function is specifically designed for FEP documents and is not applicable to other types of content
Technical threshold: Configuration requires certain technical knowledge, especially for permission settings

How to Use

Install the Runtime Environment
Ensure that the Deno runtime environment is installed on the system. If not installed, you can download and install it from the official Deno website.
Run the FEP MCP Server
Use Deno to run the MCP server. Necessary permissions need to be granted, including file read and write, network access, etc.
Configure the AI Client
Configure the MCP server in your AI assistant client. The following is a configuration example for Claude Desktop.
Start Using
Restart the AI assistant client, and now you can access FEP documents through natural language commands.

Usage Examples

Research the authentication mechanism of the Fediverse
You are developing a Fediverse application and need to understand the existing authentication and authorization mechanisms. Through the FEP MCP server, you can quickly find relevant technical proposals.
Understand the latest extensions of ActivityStreams
You need to understand the latest extensions and implementations of ActivityStreams in the Fediverse to correctly parse and process ActivityStreams data in your application.
Track the status changes of a specific proposal
A FEP proposal you are concerned about was previously in the draft state, and now you want to check if it has entered the final state or been withdrawn.

Frequently Asked Questions

Why is this MCP server needed? Can't I directly access the FEP website?
Will FEP documents be automatically updated?
What permissions do I need to run this server?
Can it be used in other AI assistants besides Claude?
What is FEP? Why is it important?

Related Resources

FEP Official Website
The official portal of FEP, containing the index and basic information of all proposals
FEP Code Repository
The source code repository of FEP documents, hosted on the Codeberg platform
Model Context Protocol Official Website
The official website of the MCP protocol, containing protocol specifications and development documents
Deno Official Website
The official website of the Deno runtime environment, providing installation guides and documentation
JSR Package Registry
The package page of the FEP MCP server on the JSR (JavaScript Registry)
GitHub Project Repository
The source code repository of the FEP MCP server, containing issue tracking and contribution guidelines

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
9.1K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.7K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
14.5K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
7.7K
4 points
P
Paperbanana
Python
8.7K
5 points
F
Finlab Ai
FinLab AI is a quantitative financial analysis platform that helps users discover excess returns (alpha) in investment strategies through AI technology. It provides a rich dataset, backtesting framework, and strategy examples, supporting automated installation and integration into mainstream AI programming assistants.
8.4K
4 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
9.3K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
9.6K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.3K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
38.5K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
79.1K
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.6K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
37.8K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
69.9K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
105.0K
4.7 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.6K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase