skills-mcp
Enables Claude/MCP agents to search, list, get details, and generate install commands for skills, MCP servers, and connections from the DFL Forge skills registry.
README
skills-mcp — DFL Forge skill-search MCP
Remote MCP server (Streamable HTTP) that exposes the live DFL Forge skills registry as MCP tools, so any Claude/MCP agent can discover and install DevFellowship skills, MCP servers and connections.
It is a thin server: no database, no state. Every tool call proxies the live
skills.sh-compatible API at https://skills.devfellowship.com.
Tools
| Tool | Signature | API |
|---|---|---|
search_skills |
(query: string, opts?: { limit?, kind?, semantic? }) |
GET /api/v1/skills/search |
get_skill |
(id: string) where id = "owner/repo/slug" |
GET /api/v1/skills/:owner/:repo/:skill |
list_skills |
(opts?: { kind?, sort? }) |
GET /api/v1/skills |
install_skill |
(id: string, opts?: { agents?: string[], scope?: "project"|"global" }) |
— returns command only |
kind is one of skill | mcp | connection | all.
install_skill does not touch the filesystem (a remote MCP can't). It returns the
exact command, e.g. npx skills add devfellowship/<repo> -g, plus a one-line explanation —
the host agent or user runs it.
All tools return structured JSON text content (and structuredContent).
Run locally
npm install
npm run build
npm start # listens on :3041 (PORT env to override)
Health check:
curl -s http://localhost:3041/health
# {"status":"ok","service":"dfl-mcp-skills","version":"0.1.0","upstream":"https://skills.devfellowship.com"}
MCP endpoint: POST http://localhost:3041/mcp (stateless Streamable HTTP).
Environment
| Var | Default | Purpose |
|---|---|---|
PORT |
3041 |
HTTP listen port |
SKILLS_API_URL |
https://skills.devfellowship.com |
Upstream registry base URL |
SKILLS_API_TIMEOUT_MS |
15000 |
Per-request upstream timeout |
Register with Claude (~/.claude.json)
Point at the deployed remote endpoint:
{
"mcpServers": {
"dfl-mcp-skills": {
"type": "http",
"url": "https://skills.mcp.devfellowship.com/mcp"
}
}
}
Restart Claude to load it. For local dev, swap the URL for http://localhost:3041/mcp.
Deploy
Containerized via the included Dockerfile. Deploy target: Dokploy →
skills.mcp.devfellowship.com. Infra is owned by another stream — this repo only
ships the build manifest; it does not provision the deployment.
- Container listens on
PORT(default3041); expose it behind the Dokploy proxy. - Health endpoint for the proxy/Dokploy probe:
GET /health.
Stack
TypeScript (strict) · @modelcontextprotocol/sdk Streamable HTTP transport · Express · zod · Node 20.
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.