Fermah MCP Community
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
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/mcpWebsite: https://fermah.gogettest.online/
Documentation: https://fermah.gogettest.online/docs
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/mcpWindsurf
{
"mcpServers": {
"fermah-mcp": {
"serverUrl": "https://fermah.gogettest.online/mcp"
}
}
}Related MCP server: Shelby docs 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 devThe 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:mcpRun the production server:
PUBLIC_BASE_URL=http://127.0.0.1:8834 npm startSecurity 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
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Public read-only MCP server for Genvernium product and developer resources.
Public, read-only MCP server for FarmNeural company facts, packages, and capabilities.
MCP server for opencode documentation, generated by doc2mcp.
MCP server for learnhouse documentation, generated by doc2mcp.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides comprehensive access to MCP documentation through structured guides, full-text search, and interactive development workflows for building servers and clients.323 npmMIT
- AlicenseBqualityDmaintenanceA read-only MCP server that provides searchable access to the Shelby documentation bundle for MCP-compatible clients. It enables users to search, list, and read documentation pages directly within AI tools and IDEs.4MIT
- AlicenseAqualityDmaintenanceAn MCP server that serves documentation and enables AI-powered search, Q\&A, and document analysis for developer tools and guides.54MIT
- AlicenseAqualityBmaintenanceAn MCP server that lets AI agents search and read documentation built with Verso, Lean's documentation authoring tool, by providing tools like search and fetch_page over configured documentation sites.418 PyPI1Apache 2.0