广告合作
MCP.so
登录

MyAIServ: AI-Powered FastAPI Server with MCP Server

@eagurin

代码仓库

基本信息

分类

开发工具

许可证

MIT

传输方式

stdio

作者

eagurin

关于 MyAIServ: AI-Powered FastAPI Server with MCP Server

High-performance FastAPI server implementing Model Context Protocol (MCP) for seamless integration with Large Language Models (LLMs). Built with modern stack: FastAPI, Elasticsearch, Redis, Prometheus, and Grafana.

#myaiserv#fastapi#ai-server

MyAIServ: AI-Powered FastAPI Server with MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "myaiserv": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

MyAIServ: AI-Powered FastAPI Server with MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MyAIServ: AI-Powered FastAPI Server with MCP 🚀?

MyAIServ is a FastAPI implementation of the Model Context Protocol (MCP), providing a standardized interface for interaction between LLM models and applications. It is intended for developers who need a high-performance, extensible API that bridges LLMs with tools, resources, and real-time communication.

How to use MyAIServ: AI-Powered FastAPI Server with MCP 🚀?

Clone the repository, install Poetry, then run poetry install to set up dependencies. Start the server with poetry run uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload or via the just run command. The API is then accessible at http://localhost:8000, with Swagger UI at /docs, ReDoc at /redoc, and GraphQL Playground at /graphql.

Key features of MyAIServ: AI-Powered FastAPI Server with MCP 🚀

  • High-performance API built on FastAPI with async operations
  • Full MCP support for resources, tools, prompts, and sampling
  • Prometheus/Grafana monitoring with metrics at /metrics
  • Extensible via simple interfaces for new tools
  • GraphQL API for flexible data queries
  • WebSocket support for real-time interactions
  • Semantic search integration with Elasticsearch
  • Redis caching for improved performance

Use cases of MyAIServ: AI-Powered FastAPI Server with MCP 🚀

  • Providing LLMs with standardized access to tools like file operations, weather, text analysis, and image processing
  • Real-time data exchange between applications and LLMs via WebSocket
  • Flexible data querying and mutation using GraphQL
  • Monitoring API usage and performance metrics in production

常见问题

1

What are the runtime dependencies?

Python 3.9+ and Poetry are required. Redis and Elasticsearch are optional but recommended for caching and semantic search.

2

How do I run tests?

Tests can be run using `poetry run pytest` or `just test`.

3

Does the server support Docker?

Yes, the project includes a `docker-compose.yml` for containerized deployment. You can run all services with `docker compose up -d`.

4

How can I integrate this with an LLM?

Retrieve available tools via GET `/tools`, then include those tools in your LLM API request (e.g., using `tools` and `tool_choice: "auto"` in the chat completion call).

5

What metrics are exposed?

Prometheus metrics are available at `/metrics`, including request counts per tool, execution times, and error counts.

评论

开发工具 分类下的更多 MCP 服务器

Eddyter AI Rich Text Editor MCP

EddyterAI

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

9

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

1

Official Porkbun MCP Server

Porkbun LLC

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac

32

offprompt

offprompt

MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

2

LocalCan

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

82
广告合作