Fermah MCP Community
A public, read-only MCP server for researching Fermah products and documentation, with tools for searching docs, reading pages, listing products and proof systems, and generating non-binding project outlines.
README
Fermah MCP Community
A public, read-only Model Context Protocol server that helps AI clients research Fermah and outline possible integrations. It exposes source-linked product and documentation lookup, proof-system metadata, and a conservative project-planning tool over Streamable HTTP.
This is a community project. It is not affiliated with or endorsed by Fermah, and it cannot submit proofs, move assets, execute Kernel workflows, or perform any other write action.
Connect
Public endpoint:
https://fermah.gogettest.online/mcp
- Website: https://fermah.gogettest.online/
- Documentation: https://fermah.gogettest.online/docs
- Health: https://fermah.gogettest.online/health
- Machine-readable manifest: https://fermah.gogettest.online/.well-known/mcp.json
No API key is required.
Claude
Open Settings → Connectors → Add custom connector and paste the public endpoint.
Cursor
Use the Add to Cursor button on the website, or add this to your MCP configuration:
{
"mcpServers": {
"fermah-mcp": {
"url": "https://fermah.gogettest.online/mcp",
"headers": {}
}
}
}
Visual Studio Code
Use the Install in VS Code button on the website, or add:
{
"servers": {
"fermah-mcp": {
"type": "http",
"url": "https://fermah.gogettest.online/mcp"
}
}
}
Codex
codex mcp add fermah-mcp --url https://fermah.gogettest.online/mcp
Windsurf
{
"mcpServers": {
"fermah-mcp": {
"serverUrl": "https://fermah.gogettest.online/mcp"
}
}
}
Capabilities
The server publishes six tools:
search_fermah_docs— search the curated official-source map.read_fermah_page— fetch one allowlisted Fermah page live.list_fermah_products— compare Kernel, Froben, Flashcast Social, and Marina.list_supported_proof_systems— return supported and planned systems from the Froben docs.design_fermah_project— produce a non-binding Kernel/Froben architecture outline.get_fermah_mcp_info— describe this endpoint and its safety model.
It also publishes two resources (fermah://overview, fermah://proof-systems) and the evaluate-fermah-fit prompt.
Local development
Requires Node.js 20.11 or newer.
npm ci
npm run dev
The Vite UI runs on its development port and the MCP service runs on 127.0.0.1:8834.
Build and verify:
npm run build
npm test
npm run test:mcp
Run the production server:
PUBLIC_BASE_URL=http://127.0.0.1:8834 npm start
Security model
- All MCP tools are read-only and require no credentials.
- Live page retrieval is restricted to a compile-time allowlist; callers cannot provide arbitrary URLs.
- Request bodies are capped at 256 KB and the MCP endpoint is rate-limited per client IP.
- Search summaries and architecture suggestions are labeled as community-maintained context.
- Current access, pricing, SLAs, network availability, and product commitments must be confirmed with Fermah.
Please report security issues privately to the repository owner rather than opening a public exploit report.
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.