MCP Local FastMCP Server
A FastMCP server providing web search, scraping, image extraction, and mail placeholders, with persistent storage and Docker deployment.
README
MCP Local FastMCP Server
This repo keeps the existing Docker/GitHub Actions deployment and rollback wrapper, but replaces the demo Nginx HTML page with a lightweight Python FastMCP server.
What changed from the demo app
- Removed the Nginx demo app.
- Removed
index.html. - Added FastMCP Python application under
app/. - Added pinned Python dependencies in
requirements.txt. - Container now listens on internal port
8000. - Host port remains controlled by
APP_PORT, default127.0.0.1:8002. - MCP endpoint:
http://127.0.0.1:8002/mcp. - SearXNG runs as an internal Docker service for free search.
- Tavily can be enabled as fallback by setting
TAVILY_API_KEY. - Reference records are saved to the
mcp-dataDocker volume as JSONL. - Mail and real DB providers are abstract placeholders for later implementation.
Run locally
cp .env.example .env
docker compose --env-file .env up --build
MCP endpoint on the host:
http://127.0.0.1:8002/mcp
Deploy locally using existing deployment flow
./scripts/deploy-local.sh
Available MCP tools
health_checkweb_searchweb_search_and_scrapescrape_urlextract_image_urlsmail_searchabstract placeholdermail_readabstract placeholdermail_create_draftabstract placeholdermail_send_draftabstract placeholder
Persistent data
Scraped references are stored at /data/references.jsonl inside the container, backed by the mcp-data Docker volume.
Production note
Keep HOST_BIND=127.0.0.1 unless you intentionally want the MCP endpoint reachable from outside the server. Caddy can continue reverse proxying to 127.0.0.1:8002 if needed.
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.