MCP
python3 -m venv .venv 或 python -m venv .venv source .venv/bin/activate pip install --upgrade pip pip install -r requirements.txt .venv\Scripts\python.exe app.py
本地 MCP + Groq + OpenAI Agents SDK
本课堂示例包含:
app.py:一个持久的本地 Streamable HTTP MCP 服务器,带有多个工具。mcp_groq_agent.ipynb:一个智能体,用于发现并调用这些工具。
设置
使用 Python 3.10 或更高版本。在终端中进入本项目文件夹,创建
虚拟环境,并安装服务器和笔记本所需的全部依赖
(如有必要,请将 python3.11 替换为你所使用的现代 Python 命令):
cd /Users/somenathmandal/Documents/transfer/grok-playground/MCP
python3.11 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt根据示例创建 .env 文件,并将你的 Groq API 密钥放入其中:
cp .env.example .envGROQ_API_KEY=replace_with_your_groq_key
GROQ_MODEL=openai/gpt-oss-20b切勿提交或分享 .env 文件;它已被 .gitignore 排除。
Related MCP server: Enterprise MCP Gateway and Tool Registry
运行 MCP 服务器
在一个终端中启动 MCP 服务器,并让它保持运行:
source .venv/bin/activate
.venv/bin/python app.pyStreamable HTTP 端点现在可通过以下地址访问:
http://127.0.0.1:8000/mcp保持该终端处于打开状态。想停止服务器时,按 Ctrl+C。
运行智能体笔记本
在第二个终端中:
cd /Users/somenathmandal/Documents/transfer/grok-playground/MCP
source .venv/bin/activate
jupyter lab mcp_groq_agent.ipynb如果 Jupyter 提示,请选择 .venv Python 内核,然后从上到下
运行这些单元格。该笔记本直接连接到 http://127.0.0.1:8000/mcp;它从不
启动或导入 app.py。Groq API 密钥从 .env 加载,且从不
存储在笔记本中。
各部分如何连接
Notebook agent
-> Groq OpenAI-compatible API (model reasoning and tool selection)
-> http://127.0.0.1:8000/mcp (tool discovery and execution)
-> app.py MCP tools在执行 MCP 连接单元格之前,服务器必须处于运行状态。如果
笔记本报告连接错误,请首先确认服务器终端显示
Uvicorn 正在 http://127.0.0.1:8000 上运行。
笔记本还会防范偶尔从笔记本启动器继承的过期证书文件环境变量。 仅在引用的路径不存在时,它才会移除证书变量; 有效的自定义证书设置会被保留。
MCP
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Hosted MCP runtime where the agent is the operator: sign up by tool call, publish your own tools.
Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceExposes MCP tools that enable remote LLMs to query local Docker containers, OS processes, and system services in real time.-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.1MIT
- FlicenseNot gradedqualityAmaintenanceEnables MCP-compatible AI clients to invoke CLI-driven agent tools over Streamable HTTP, including shell execution, file operations, patching, image viewing, web search, and nested agent tasks, with permission modes and real-time progress streaming.-
- FlicenseNot gradedqualityCmaintenanceEnables agents to discover and execute local tools via a Streamable HTTP endpoint using the Groq OpenAI-compatible API.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/diposhreeroy/MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server