Firecrawl Server for MCP
radu103
README
Firecrawl Server for MCP
Express API server for Firecrawl that provides endpoints for web crawling and scraping functionality.
Features
- Scrape a single URL
- Scrape multiple URLs in batch
- Crawl a website and scrape all pages
Docker Setup
This project can be easily run using Docker and Docker Compose. Docker Compose allows you to define, manage, and run multi-container Docker applications with ease.
Prerequisites
Docker Compose Commands
Build and Start the Container
# Build and start in detached mode
docker compose up -d
# Build the image without starting the container
docker compose build
# Build with no cache (force rebuild)
docker compose build --no-cache
# Build and start with logs in console (not detached)
docker compose up
Manage the Container
# Stop the container
docker compose stop
# Stop and remove the container
docker compose down
# Stop and remove the container and volumes
docker compose down -v
# View container logs
docker compose logs
# Follow container logs
docker compose logs -f
# Restart the container
docker compose restart
Scaling (if needed)
# Scale the service to multiple instances
docker compose up -d --scale firecrawl-server=3
Tag and upload
docker tag firecrawl-server-for-mcp-tools yourusername/firecrawl-server-for-mcp:latest
docker tag firecrawl-server-for-mcp-tools yourusername/firecrawl-server-for-mcp:0.0.1
docker push radu103/firecrawl-server-for-mcp:latest
docker push radu103/firecrawl-server-for-mcp:0.0.1
Docker Compose File
The project includes a docker-compose.yml
file that configures:
- Port mapping (3000:3000)
- Environment variables
- Volume for persistent storage of downloaded files
API Endpoints
GET /
: Home route that displays API informationPOST /scrape
: Scrape a single URLPOST /scrape-batch
: Scrape multiple URLsPOST /crawl
: Crawl a website and scrape all pages
Sample Requests
Check the sample_requests
directory for HTTP request examples.
Development
Installation Without Docker
# Install dependencies
npm install
# Start server
npm start
The server runs on port 3000 by default or the port specified in the PORT environment variable.
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.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.