fastcrw/crw

❌ 实测失败serverRustAGPL-3.0★ 1241

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.

实测结果

失败

沙箱内启动/握手失败，下方给出失败阶段与原始报错。失败阶段：initialize，错误类型：runtime_error。这类信息对判断“是不是我这边的环境问题”很有用，原始报错见下。

error_type: runtime_error

)
             ^^^^^^
  File "/work/venv/lib/python3.12/site-packages/crw/__main__.py", line 10, in main
    binary = ensure_binary()
             ^^^^^^^^^^^^^^^
  File "/work/venv/lib/python3.12/site-packages/crw/_binary.py", line 193, in ensure_binary
    return _download_binary(tag)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/work/venv/lib/python3.12/site-packages/crw/_binary.py", line 96, in _download_binary
    expected = _expected_digest(tag, asset)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/work/venv/lib/python3.12/site-packages/crw/_binary.py", line 72, in _expected_digest
    raise CrwBinaryNotFoundError(
crw.exceptions.CrwBinaryNotFoundError: could not reach GitHub to fetch SHA256SUMS for v0.43.2: <urlopen error [Errno -3] Temporary failure in name resolution>. Set CRW_BINARY=/path/to/crw-mcp to use a binary you already have, or install one with: cargo install crw-mcp

安装方式: uvx
包名: crw
解析依据: pypi package lookup
沙箱: docker
总耗时: 6005 ms
安装耗时: 4776 ms
工作目录: 1 MB
探针版本: 1.0.0
实测时间: 2026-11-11 14:17:13

如何使用

❌ 实测失败runtime_error · )；下面配置仅供参考，跑不跑得通取决于你的环境

1安装 / 启动命令uv / uvx

uvx crw

2客户端配置Claude Desktop / Cursor

{
  "mcpServers": {
    "fastcrw-crw": {
      "command": "uvx",
      "args": [
        "crw"
      ]
    }
  }
}

整段粘进 claude_desktop_config.json 的 mcpServers 里（Cursor 用 ~/.cursor/mcp.json），保存后重启客户端。

安装方式来源：pypi package lookup，沙箱实测未通过。

打开 GitHub 仓库 ↗项目主页 ↗MCP 体检工具

仓库信息

全名: fastcrw/crw
分类: server
Stars: 1241
Forks: 96
主要语言: Rust
License: AGPL-3.0
最近推送: 2026-11-10
仓库创建: 2026-03-02
首次收录: 2026-11-10
最近抓取: 2026-11-10

#ai#ai-agents#crawler#data-extraction#docker#firecrawl-alternative#html-to-markdown#llm#markdown#mcp#mcp-server#rust