Analysis MCP Server

Analysis MCP Server

Enables arithmetic operations such as addition and calculating averages, exposing tools via MCP with stdio and Streamable HTTP transports.

Category
Visit Server

README

Agent Platform — Phase 1 MCP

本目錄依照 AI Agent + MCP Server 建置說明 v0.1.md 建立。目前已完成單一 Analysis MCP Server、兩個工具、stdio 與 localhost Streamable HTTP transport,以及兩種 transport 的整合測試。

目前架構

mcp_server/
├── mcp_servers/
│   └── analysis/
│       ├── server.py
│       └── tests/
├── .env.example
├── .gitignore
├── AGENTS.md
├── README.md
└── requirements.txt

目前提供:

  • add(a, b):兩數相加。
  • calculate_average(values):計算非空數列的算術平均值。

安裝

需要 Python 3.10 以上;目前已在 Python 3.12 驗證。

cd /home/mingkang/mcp_server
python3 -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install -r requirements.txt

執行 MCP Server(Streamable HTTP)

source .venv/bin/activate
python mcp_servers/analysis/server.py

預設 endpoint:

http://127.0.0.1:8001/mcp

Server 刻意只監聽 localhost;目前沒有驗證、授權與 TLS,不得改用 0.0.0.0 對外公開。

如需直接啟動 stdio transport:

python mcp_servers/analysis/server.py --transport stdio

不要在 stdio Server 中把一般日誌寫到 stdout,以免破壞 MCP 訊息。

執行測試

source .venv/bin/activate
pytest

測試包含 Python 函式單元測試,以及真正啟動 stdio 和 Streamable HTTP MCP 子行程後進行 initialize、tools/list、tools/call 的整合測試。HTTP 測試使用動態 localhost port,避免與開發中的 8001 衝突。

MCP Inspector

環境已具備 Node.js 與 npx 時可執行:

source .venv/bin/activate
mcp dev mcp_servers/analysis/server.py

Inspector 應顯示 addcalculate_average。建議測試:

  • adda=5, b=7,預期 12
  • calculate_averagevalues=[10,20,30],預期 20
  • calculate_averagevalues=[],預期回報 values cannot be empty

下一個 checkpoint

stdio、Inspector 與 localhost Streamable HTTP 驗收通過後,下一步是串接單一 OpenAI Agent。目前 PyPI 的 openai-agents==0.19.4 宣告相依 mcp>=1.19,<2,與本專案採用的 mcp==2.0.0 不相容;因此尚未安裝 Agents SDK,也不以忽略相依條件的方式強行混裝。

.env 已建立且被 Git 忽略;日後 Agent 階段再填入 OPENAI_API_KEY,切勿提交金鑰。

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured