mcp-tool-gateway
Click on "Install 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., "@mcp-tool-gatewayScrape https://example.com and summarize the page content."
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.
mcp-tool-gateway
项目简介
基于标准 MCP(Model Context Protocol)协议开发的通用工具调度网关,实现多远端工具进程统一管理,解决 Agent 工具硬耦合、无法跨业务复用问题。
内置网页爬取、文本摘要、向量知识库检索三类标准化 Skills,服务端通过list_tools暴露全部工具元数据、call_tool统一分发业务逻辑;客户端批量启停 MCP 服务并建立工具路由映射,自动将工具转换为 LLM Function Calling 标准格式,支持大模型自主识别、调用远端能力。
可无缝对接 CrewAI 多智能体、ReAct 对话 Agent,已配套法律文档检索、智能客服两大 RAG 业务场景落地验证,新增业务工具仅需独立开发 MCP 服务,无需修改 Agent 核心调度逻辑,大幅降低研发工具接入成本。
技术栈
Python / MCP SDK / Crawl4AI / OpenAI Function Calling / 多进程调度
核心能力
单 MCP 服务支持多业务工具注册与统一分发
批量管理多 MCP 进程,自动维护工具名路由映射
MCP 工具自动适配大模型 Function Calling 规范
内置检索、爬虫、文本处理开箱即用工具
进程异常捕获、安全启停资源回收机制
配套业务项目
法律多智能体 RAG 系统:https://github.com/zike678/paralegal-agent
客服 ReAct 对话智能体:https://github.com/zike678/Robot_Vacuum_Agent
使用方式
安装依赖:
uv sync/pip install -r requirements.txt启动 MCP 服务端:
python mcp_server.py多服务调度测试:
python mcp_multi_client.pyLLM 自动调用 Demo:
python agent_llm_entry.py
极简短版(仓库顶部一句话简介,用于 Github 仓库主页短描述)
通用 MCP 标准化工具网关,多进程统一调度,打通 LLM 与远端检索、爬虫等业务工具,可复用至多套 RAG Agent 智能体项目
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
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/zike678/mcp-tool-gateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server