经 AI Skill Hub 精选评估,vecgrep:Cursor-style semantic code search 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
vecgrep是开源的MCP工具,用于Claude Code的Cursor-style semantic code search,提供了语义代码搜索功能,方便开发者快速找到所需代码。
vecgrep:Cursor-style semantic code search 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
vecgrep是开源的MCP工具,用于Claude Code的Cursor-style semantic code search,提供了语义代码搜索功能,方便开发者快速找到所需代码。
vecgrep:Cursor-style semantic code search 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/VecGrep/vecgrep
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"vecgrep-cursor-style-semantic-code-search": {
"command": "npx",
"args": ["-y", "vecgrep"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 vecgrep:Cursor-style semantic code search 执行以下任务... Claude: [自动调用 vecgrep:Cursor-style semantic code search MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"vecgrep_cursor-style_semantic_code_search": {
"command": "npx",
"args": ["-y", "vecgrep"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Cursor-style semantic code search as an MCP plugin for Claude Code.
Instead of grepping 50 files and sending 30,000 tokens to Claude, VecGrep returns the top 8 semantically relevant code chunks (~1,600 tokens). That's a ~95% token reduction for codebase queries.
Requires Python 3.12 and uv.
Note: Python 3.12 is required — tree-sitter-languages does not yet have wheels for Python 3.13+.
pip install vecgrep # standard pip
uv tool install --python 3.12 vecgrep # uv tool (recommended)
| Mode | Avg tokens returned | vs raw read | Savings |
|---|---|---|---|
| Raw file read (baseline) | 26,009 | — | — |
search_code (top_k=8) | ~3,007 | 11.6% | **88%** |
hybrid_search (top_k=8) | ~3,324 | 12.8% | **87%** |
search_graph (limit=8) | ~47 | 0.2% | **>99%** |
search_graph returns structured node metadata only (name, kind, file, line range) — no source code — so it's ultra-cheap for structural questions ("where is X defined?", "what calls Y?").
You don't trigger VecGrep manually - Claude decides when to call the tools based on what you ask.
| What you say to Claude | Tool invoked |
|---|---|
| "Index my project at /Users/me/myapp" | index_codebase |
| "How does authentication work in this codebase?" | search_code |
| "Find where database connections are set up" | search_code |
| "How many files are indexed?" | get_index_status |
| "Build a knowledge graph of my project" | index_graph |
| "What calls the VectorStore.search method?" | search_graph + graph_neighbors |
| "Find code structurally related to authentication" | hybrid_search |
Typical first-time flow:
You: "Search for how payments are handled in /Users/me/myapp"
Claude: [calls index_codebase automatically since no index exists]
Claude: [calls search_code with your query]
Claude: "Here's how payments work — in src/payments.py:42..."
After the first index, subsequent searches skip unchanged files automatically — no re-indexing needed unless your code changes.
VecGrep can be tuned via environment variables:
export VECGREP_OPENAI_KEY=sk-...
Run once — works for every project:
claude mcp add --scope user vecgrep -- vecgrep
This installs VecGrep as a persistent binary and registers it in your user config (~/.claude.json) so it's available globally across all projects. Starts instantly — no download delay on Claude Code launch.
vecgrep是一个简单易用的MCP工具,提供了语义代码搜索功能,适合需要快速找到代码的开发者,但功能有限,需要进一步开发和完善。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:vecgrep:Cursor-style semantic code search 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | vecgrep |
| 原始描述 | 开源MCP工具:Cursor-style semantic code search as an MCP plugin for Claude Code. Instead of 。⭐6 · Python |
| Topics | claudeclaude-codemcppython |
| GitHub | https://github.com/VecGrep/vecgrep |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-09 · 更新时间:2026-06-11 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端