FastMCP Forge
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@FastMCP Forgescaffold a new MCP project called analytics-mcp with tests"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
FastMCP Forge (Lite Edition)
FastMCP Forge is an ergonomic framework and CLI scaffolding engine that enables Python developers to build, test, and package compliant Model Context Protocol (MCP) servers in seconds.
⚡ The Problem: MCP Boilerplate Burnout
In 2026, every AI developer is building MCP servers to connect tools to Claude Desktop, Cursor, Windsurf, and Antigravity. However, writing raw JSON-RPC 2.0 handlers from scratch requires:
Manually parsing JSON schemas for tool arguments.
Handling error codes (-32600, -32601, -32602, -32000).
Managing
sys.stdinandsys.stdoutstream buffers.Writing test harnesses to mock agent tool invocations.
FastMCP Forge gives you an intuitive @app.tool decorator that introspects function signatures, infers types, generates valid schemas, and creates automated test suites instantly.
Related MCP server: mcpserve
🛠️ Code Example: Build an MCP Server in 10 Lines
from fastmcp_forge.server import FastMCP
app = FastMCP(name="math-mcp", version="1.0.0")
@app.tool(description="Multiply two numbers safely")
def multiply(a: float, b: float) -> float:
return a * b
if __name__ == "__main__":
app.run_stdio()🚀 CLI Project Scaffolder
Generate a full production-ready project with tests in 1 second:
python -m fastmcp_forge.cli new analytics-mcpOutput:
[OK] Created new FastMCP project 'analytics-mcp'
Generated files:
- server.py
- tests/test_server.py
- README.md
- requirements.txt🖥️ Client Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"my-server": {
"command": "python",
"args": ["server.py"],
"cwd": "/path/to/my-server"
}
}
}💎 Need Enterprise Remote Deployment? Upgrade to FastMCP Forge Pro
Deploying MCP servers as remote team microservices, behind authentication proxies, or in production clouds?
Feature | Lite (Open Source) | Pro ($14.99 USD) |
@tool Schema Introspection | ✅ | ✅ |
JSON-RPC 2.0 stdio Transport | ✅ | ✅ |
CLI Project Scaffolding | ✅ | ✅ |
Dual Transport: stdio + Remote SSE HTTP | ❌ | ✅ |
Security & Auth Middleware (API Keys & Bearer Tokens) | ❌ | ✅ |
Token Bucket Rate Limiter | ❌ | ✅ |
Structured JSON Logs with Correlation IDs | ❌ | ✅ |
Multi-Stage Docker & Compose | ❌ | ✅ |
Full Pytest Suite & Enterprise Architecture Blueprint | ❌ | ✅ |
👉 Get FastMCP Forge Pro on Gumroad ($14.99)
📄 License
MIT License. See LICENSE for details.
This server cannot be deployed
Maintenance
Related MCP Connectors
- TypeshipOAuthdev.typeship
Generate a typed SDK, CLI, and MCP server from any OpenAPI or GraphQL spec, and keep them current.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP Spec Compliance MCP — audits any MCP server.json against the official Model Context Protocol
Free MCP tools to validate multi-agent coordination thread turns and retrieve schema/samples.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables building lightweight MCP servers where Rust handles transport, routing, and schema validation while Python defines tool behavior using type hints, with support for stdio and HTTP transports.MIT
- AlicenseNot gradedqualityBmaintenanceA minimal, decorator-based framework for building MCP servers in Python with zero dependencies. It enables you to define tools and resources via simple decorators, handling JSON-RPC protocol, type inference, and stdio transport automatically.MIT
- AlicenseNot gradedqualityCmaintenanceEnables turning any command-line tool into an MCP server with auto-generated JSON schema, supporting stdio, timeouts, and stderr capture.MIT
- AlicenseAqualityBmaintenanceEnables building and running zero-dependency MCP servers with automatic JSON Schema generation, exposing Python tools to Claude Desktop, Cursor, and autonomous agent fleets.2Apache 2.0