Skip to main content
Glama
modou-tools-mcp

modou-tools-mcp

by xihongshi567

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"]
    }
  }
}

Related MCP server: Agent中国通

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

Tool

Purpose

Network

web_search

Chinese web search (SearXNG aggregation, only available in local deployment)

Local

fetch_page

Web page content extraction, denoised Markdown output (trafilatura)

Direct

fetch_hot_topics

Hot list aggregation (知乎/B站/GitHub/HN)

Direct

github_search_repos / github_compare_repos

GitHub repository trends/comparison (60 req/h, 5,000 req/h with token)

Direct

arxiv_search

arXiv paper search (supports categories/advanced syntax, sorted by relevance or latest)

Direct

exa_search

English semantic search (Exa free endpoint, no key required)

Direct

juejin_recommended / juejin_by_category

掘金 tech community article discovery (recommended feed/category browsing)

Direct

sec_company_facts / sec_compare_companies

US stock financial reports (SEC EDGAR free)

Available, slower

cninfo_company_profile / cninfo_financial_analysis / cninfo_compare_companies

A-share financial reports (东方财富 public API)

Direct

parse_pdf

PDF report → Markdown + tables (PyMuPDF)

Local

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

Variable

Description

Required

GITHUB_TOKEN

GitHub API token, increases the rate limit to 5,000 req/h

Optional

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)

Available Tools

15 tools
cninfo_company_profileCninfo Company ProfileB

查询 A股公司基本信息(东方财富公开接口)。

Inputs: code (required), market. Returns: object

cninfo_compare_companiesCninfo Compare CompaniesA

对比多家 A股公司最新财年核心指标。

Inputs: codes (required), years. Returns: object

cninfo_financial_analysisCninfo Financial AnalysisA

查询 A股公司财务分析指标(ROE/净利率/营收增速/毛利率/研发占比)。

Inputs: code (required), years. Returns: object

fetch_hot_topicsFetch Hot TopicsA

获取主流平台当前热搜榜单(zhihu 知乎 / bilibili B站 / github GitHub 趋势 / hackernews HN)。

Inputs: platforms. Returns: object

fetch_pageFetch PageA

抓取网页正文,自动去广告/导航/侧边栏,输出干净 Markdown(trafilatura)。

Inputs: url (required), max_chars, include_links. Returns: object

github_compare_reposGithub Compare ReposB

对比多个 GitHub 仓库的当前快照数据。

Inputs: repos (required). Returns: object

github_search_reposGithub Search ReposA

搜索 GitHub 仓库趋势,把技术趋势翻译成数字(stars/forks/活跃度)。

Inputs: query (required), sort, limit. Returns: object

juejin_by_categoryJuejin By CategoryB

按分类浏览掘金文章(ai / frontend / backend / android / ios / freebie / article)。

Inputs: category (required), limit. Returns: object

parse_pdfParse PdfA

解析 PDF 报告为 Markdown(保留表格),本地文件或在线 URL 均可。

Inputs: url, file_path, max_pages, extract_tables. Returns: object

sec_company_factsSec Company FactsB

查询美股公司财报(SEC EDGAR),拿营收/净利/研发支出等结构化数据。

Inputs: cik, years, ticker, metrics. Returns: object

sec_compare_companiesSec Compare CompaniesA

对比多家美股公司同一财年的核心指标。

Inputs: tickers (required), years, metrics. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 15 tools

    Disambiguation4/5

    Tools are mostly distinct by source and purpose (search vs. compare vs. fetch vs. parse), but a few could be confused: web_search vs exa_search both handle search, and juejin_recommended vs juejin_by_category both return Juejin articles.

    Naming Consistency3/5

    All names use snake_casecars but follow inconsistent patterns: some are source_verb_object (github_search_repos), some are verb_object (fetch_page), and some are source_attribute (juejin_recommended, cninfo_company_profile). The naming is readable but not fully predictable.

    Tool Count4/5

    15 tools is at the upper boundary of a reasonable scope for a research/investment aggregation servercars. Each tool maps to a distinct data source or operation, though the count is getting close to heavy.

    Completeness4/5

    Covers searching, fetching content, financial data, and comparison workflows across multiple sources. Minor gaps exist (e.g., no explicit historical data beyond current snapshots, no saved/watchlist functionality), but core research workflows are complete.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server optimized for Chinese users that enables AI models to perform Bing searches and fetch webpage content without requiring an API key. It provides specialized tools for searching and scraping web data directly through supported AI environments like Claude or Cursor.
      25 npm
      7
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      这是一个面向中文圈的MCP服务器,将中国互联网常用能力(如地图、快递、RSS、B站等)封装为标准MCP工具,方便AI Agent安全调用。
      13
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that aggregates AI news, academic papers from ArXiv, and trending GitHub repositories from multiple sources, enabling users to fetch, search, and filter recent AI content via natural language.
      1
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      This MCP server enables AI agents to read and search the internet without paid API keys, supporting multiple channels like web, GitHub, RSS, YouTube, and more, with automatic browser escalation and caching.
      -