MCPSERV.CLUB
jujumilk3

Ezmcp

MCP Server

FastAPI‑style MCP server for SSE

Stale(50)
23stars
2views
Updated 19 days ago

About

Ezmcp is a lightweight framework that lets developers quickly build MCP‑compatible servers using FastAPI‑like decorators, with automatic schema generation, type validation, and built‑in SSE support.

Capabilities

Resources
Access data sources
Tools
Execute functions
Prompts
Pre-built templates
Sampling
AI model interactions

docs_image

ezmcp is a streamlined Model Context Protocol (MCP) server framework that focuses on simplicity and performance, especially when working with Server‑Sent Events (SSE). It lets developers expose AI‑compatible tools and prompts through a familiar FastAPI‑style syntax, turning any Python function into an MCP endpoint with minimal ceremony. By handling type validation, schema generation, and SSE transport automatically, ezmcp removes the boilerplate that typically accompanies MCP server development.

The core value of ezmcp lies in its developer‑centric design. Using decorators, a function can be annotated as an MCP tool with just a line of code, and the framework will introspect its signature to build the corresponding JSON schema. This means that once a function is defined, clients can discover its parameters and expected response types without writing additional metadata. The built‑in SSE support ensures that responses can be streamed in real time, a feature essential for conversational agents and interactive workflows.

Key capabilities include:

  • FastAPI‑style middleware that can be applied globally, enabling cross‑cutting concerns such as logging, authentication, or performance metrics.
  • Automatic schema generation from Python type hints, giving clients a precise contract for tool invocation.
  • Interactive documentation accessible at , allowing developers to test tools directly from a browser without external tooling.
  • Easy integration with existing Starlette or FastAPI applications, so ezmcp can be dropped into a larger web service with no friction.

Typical use cases span from rapid prototyping of AI assistants to production deployments where reliability and low overhead are critical. For instance, a data‑analysis platform can expose a set of analytical tools as MCP endpoints; an assistant like Claude can then call these tools, receive streamed results, and incorporate them into a conversation. Because ezmcp is lightweight yet feature‑rich, it scales well in microservice architectures where multiple AI assistants may need to interact with a shared pool of tools.

In summary, ezmcp provides an out‑of‑the‑box MCP server that lowers the barrier to creating robust, type‑safe AI tool integrations. Its emphasis on SSE streaming, middleware flexibility, and automatic documentation makes it an attractive choice for developers looking to embed AI capabilities into existing Python web ecosystems.