Skip to main content
Glama
deenesjakoruzh
aabGit

research-tools

by aabGit
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

自主网络研究智能体

一个教学项目：一个 Python 智能体，能够规划、搜索网络、在 RAG 中存储笔记、撰写报告，然后自我批评并循环直到答案足够好。

技术栈：Python 3.11+ · LangChain · LangGraph · MCP · Chroma RAG · LangSmith

你正在构建的内容（课堂地图）

组件

文件

职责

配置

src/research_agent/config.py

读取 .env

LLM 层

src/research_agent/llm.py

一个函数，多种提供商

工具

src/research_agent/tools.py

搜索 + 获取页面

MCP

src/research_agent/mcp_server.py

通过 MCP 协议提供相同工具

RAG

src/research_agent/rag.py

在 Chroma 中记住页面

状态

src/research_agent/state.py

图的笔记本

节点

src/research_agent/nodes.py

每个步骤一个函数

图

src/research_agent/graph.py

连接循环

CLI

src/research_agent/cli.py

从终端运行

API

src/research_agent/api.py

FastAPI 后端

阅读 TEACHING.md 获取完整课程。

Related MCP server: Local-MCP-server

设置

cd ~/Projects/autonomous-web-research-agent
python3.11 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
cp .env.example .env

在 .env 中至少放入一个 LLM 密钥（OPENAI_API_KEY 是默认路径）。搜索功能使用免费的 DuckDuckGo。如果之后需要更高质量的搜索，可以添加 TAVILY_API_KEY。添加 LANGCHAIN_API_KEY 可在 LangSmith 中查看追踪。

运行研究任务

python -m research_agent.cli "How does MCP differ from a normal LangChain tool?"

运行后端

python -m research_agent.api
# POST http://127.0.0.1:8001/research  {"question": "..."}

运行 MCP 服务器（用于 Cursor / 其他主机）

python -m research_agent.mcp_server

示例 Cursor MCP 配置：

{
  "mcpServers": {
    "research-tools": {
      "command": "/Users/YOU/Projects/autonomous-web-research-agent/.venv/bin/python",
      "args": ["-m", "research_agent.mcp_server"]
    }
  }
}

测试（无需 API 密钥）

pytest
Install Server
F
license - not found
A
quality
B
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • Jina Reader

    Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.

  • Dewey

    Agentic search over your Dewey document collections from any MCP-compatible client.

  • ctx

    Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.

View all MCP Connectors

Latest Blog Posts

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/aabGit/Autonomous-Web-Research-Agent'

If you have feedback or need assistance with the MCP directory API, please join our Discord server