Skip to main content
Glama
deenesjakoruzh
chenxuyaun

free-web-mcp

by chenxuyaun
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

free_web_mcp

Free Web MCP —— 一个免费的 MCP Server，为 Claude / Cursor / 其他 MCP Client 提供网络搜索（DuckDuckGo，无需 API Key）与网页抓取 + 正文提取工具。

详细需求见 docs/free_web_mcp.md。

Tools

Tool

说明

web_search(query, max_results=5)

DuckDuckGo 搜索，返回 {title,url,snippet,source} 列表

web_fetch(url, rendered=False)

抓取网页并提取正文，返回 {url,title,content,text_length}；rendered=True 时驱动 headless Chromium（需 RENDER_ENABLED=true）

web_search_and_fetch(query, max_results=5, rendered=False)

搜索后逐个抓取 Top N 结果正文

Related MCP server: qsearch

快速开始

uv sync

stdio 模式（本地客户端）

uv run free-web-mcp                # 或: uv run python -m free_web_mcp

Cursor / Claude Desktop 配置示例：

{
  "mcpServers": {
    "free-web-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/free_web_mcp", "free-web-mcp"]
    }
  }
}

HTTP 模式（远程部署）

uv run free-web-mcp --transport http   # 监听 .env 中的 HOST/PORT，默认 0.0.0.0:8000
curl http://localhost:8000/health      # -> {"status":"ok","service":"free-web-mcp"}

MCP streamable-http 端点：http://<host>:8000/mcp。

Docker

# 默认：仅 HTTP 抓取路径
docker build -f docker/Dockerfile -t free-web-mcp .
docker run --rm -p 8000:8000 free-web-mcp

# 启用 headless 渲染（构建时下载 Chromium ~150MB；首次启动约 1-3s）
docker build -f docker/Dockerfile --build-arg INSTALL_PLAYWRIGHT_BROWSERS=true -t free-web-mcp:render .
docker run --rm -p 8000:8000 -e RENDER_ENABLED=true free-web-mcp:render

配置（.env）

复制 .env.example 为 .env 后按需修改；.env 不入库。

变量

默认

说明

HOST / PORT

0.0.0.0 / 8000

HTTP 监听地址

LOG_LEVEL

INFO

日志级别

HTTP_TIMEOUT

30

抓取超时（秒）

MAX_CONTENT_LENGTH

5000000

响应体大小上限（字节）

SEARCH_MAX_RESULTS

10

max_results 的硬上限

RENDER_ENABLED

false

是否启用 headless 浏览器（Playwright + Chromium）

RENDER_TIMEOUT

30

渲染超时（秒）

RENDER_MAX_BYTES

5000000

渲染后响应体大小上限

开发

uv run pytest                  # 测试
uv run ruff check .            # lint
uv run mypy                    # 类型检查（strict）

架构

严格分层：MCP Tool 层 → Service 层（SearchService/FetchService）→ Provider/HTTP 层。搜索源可插拔（当前实现：DuckDuckGoProvider），HTTP 统一走 WebClient，正文提取 trafilatura 优先、BeautifulSoup 兜底。详见 AGENTS.md。

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd
A
license - permissive license
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

  • qsearch

    theYahia
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to perform web searches with full content retrieval and multi-engine provenance, including trust scoring and local corpus persistence, via MCP integration.
    3
    2
    Apache 2.0

  • MyWebSearch MCP

    iuiu-py
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to perform unified web research through a single MCP server, including search, page fetching, recursive crawling, document parsing, YouTube transcript extraction, and deep multi-query research.
    2

View all related MCP servers

Related MCP Connectors

  • Aginx Browser

    Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.

  • web-scraper

    Web tools for agents: fetch URL as markdown (free MCP) + x402 scrape, links, AI JSON, snapshot.

  • agentsearch-mcp

    LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.

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/chenxuyaun/free_web_mcp'

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