modou-tools-mcp

A global technology intelligence hub for Chinese developers.

An MCP server that, once installed into an Agent, can gather global technology intelligence: on the English side, check GitHub trends, arXiv papers, HN hot posts, Exa semantic search, SEC US stock filings; on the Chinese side, delve into 掘金, 知乎, B站, and A-share financial reports. All tools are zero API key, zero cost, and directly accessible from mainland China — this is the biggest difference from solutions like Exa / Firecrawl / Perplexity that require subscriptions and keys.

Quick Start (Cloud-Hosted Version)

In a client that supports MCP (Claude Code / Cherry Studio / Kimi Playground, etc.), add the following configuration to connect; no local installation of any dependencies is required:

{
  "mcpServers": {
    "modou-tools": {
      "command": "uvx",
      "args": ["modou-tools-mcp@latest"]
    }
  }
}

Local Deployment (Full Functionality)

The cloud-hosted version does not include local search for compatibility reasons (see Known Limitations). For full functionality, run locally:

# 本机 Python 环境（建议 3.10+）
pip install modou-tools-mcp

{
  "mcpServers": {
    "modou-tools": {
      "command": "uvx",
      "args": ["modou-tools-mcp@latest"]
    }
  }
}

Or run directly from the repository source (development mode):

git clone https://github.com/xihongshi567/modou-tools-mcp
cd modou-tools-mcp
pip install -e .
claude mcp add modou-tools -- python "D:/okok/modou-tools-mcp/src/modou_tools_mcp/server.py"

Tool List

All tools return a unified structure: success {"ok": true, ...}; failure {"ok": false, "error": "...", "detail": "..."}.

A Complete Scenario: Researching the “RAG Technical Direction”

When the Agent receives a research task, modou-tools provides end-to-end support:

1. Kick off: use exa_search("retrieval augmented generation trends 2026") to gauge global trends

2. Supplement with academic research: use arxiv_search("cat:cs.CL AND all:RAG") to see the latest papers

3. Check the community: use juejin_recommended / fetch_hot_topics(zhihu) to see what's being discussed in China

4. Fetch original text: use fetch_page(url) to get the full text of key articles

5. Read reports: use parse_pdf(url) to parse PDF whitepapers

6. Look up data: use github_search_repos("RAG framework") to check project popularity

Design Principles

• Pure collection: no LLM processing (the Agent itself will summarize and distill), keeping the server lightweight

• Zero dependencies: no keys required except for the optional GITHUB_TOKEN; Exa uses the official free endpoint

• Errors don't interrupt: a single tool failure returns a structured error, and the Agent can try another route

Environment Variables

Development

# 离线冒烟（结构检查，不依赖网络）
python smoke_test.py

# 在线验证全部工具
python scripts/verify_online.py

Known Limitations

• web_search depends on local SearXNG (docker start searxng); this tool is unavailable in the cloud-hosted version

• GitHub without a token is limited to 60 req/h (returns a 403 notice when quota is exhausted); SEC occasionally returns 503 and can be retried; 东方财富 interface occasionally disconnects (built-in retry 3 times)

• The Exa free endpoint has quota limits and may be throttled under heavy usage

• 掘金's internal search API requires a logged-in state and is not provided; full text of 掘金 articles requires using fetch_page

• Scanned PDFs return an is_scanned=true warning (no OCR)