Analysis MCP Server
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., "@Analysis MCP ServerCalculate the average of 10, 20, and 30"
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.
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。
Related MCP server: Math Calculator MCP Server
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/mcpServer 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.pyInspector 應顯示 add 與 calculate_average。建議測試:
add:a=5,b=7,預期12。calculate_average:values=[10,20,30],預期20。calculate_average:values=[],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。
This server cannot be deployed
Maintenance
Related MCP Connectors
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
17 Base data tools for agents over Streamable HTTP MCP. Pay per call in USDC via x402; no API key.
Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
This MCP server enables users to perform scientific computations regarding linear algebra and vect…
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceProvides basic arithmetic calculation tools through an HTTP-accessible MCP server. Supports mathematical operations like addition with streamable responses for integration with MCP clients.-
- FlicenseDqualityDmaintenanceProvides basic mathematical operations (addition, subtraction, multiplication, division) through a calculate tool. Supports both stdio and HTTP/SSE transport modes.111 npm-
- FlicenseNot gradedqualityCmaintenanceExposes add, subtract, multiply, and divide as MCP tools, implemented with the FastMCP SDK and a raw stdio version.-
- FlicenseAqualityCmaintenanceEnables AI agents to perform arithmetic operations — addition, subtraction, multiplication, and division with divide-by-zero validation — through MCP tool calls. It can be run locally over stdio or as an HTTP microservice via streamable-http transport.4-