游标的本地代码索引
一个基于 Python 的实验性服务器,使用 ChromaDB在本地索引代码库,并通过 MCP(模型上下文协议)服务器为 Cursor 等工具提供语义搜索工具。
设置
克隆并进入存储库:
git clone <repository-url> cd cursor-local-indexing通过复制
.env.example创建.env文件:cp .env.example .env配置你的
.env文件:PROJECTS_ROOT=~/your/projects/root # Path to your projects directory FOLDERS_TO_INDEX=project1,project2 # Comma-separated list of folders to index例子:
PROJECTS_ROOT=~/projects FOLDERS_TO_INDEX=project1,project2启动索引服务器:
docker-compose up -d配置 Cursor 以使用本地搜索服务器:创建或编辑
~/.cursor/mcp.json:{ "mcpServers": { "workspace-code-search": { "url": "http://localhost:8978/sse" } } }重新启动 Cursor IDE 以应用更改。
服务器将开始索引您指定的项目,并且当这些项目处于活动状态时,您将能够在 Cursor 中使用语义代码搜索。
打开您配置为索引的项目。
创建一个.cursorrules文件并添加以下内容:
<instructions>
For any request, use the @search_code tool to check what the code does.
Prefer that first before resorting to command line grepping etc.
</instructions>
开始使用光标代理模式并查看它进行本地向量搜索!
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
基于 Python 的本地索引服务器,使用 ChromaDB 为代码库创建语义搜索功能,允许 Cursor IDE 对您的代码执行矢量搜索,而无需将数据发送到外部服务。
Related MCP Servers
- Asecurity-licenseAqualityA server that provides data retrieval capabilities powered by Chroma embedding database, enabling AI models to create collections over generated data and user inputs, and retrieve that data using vector search, full text search, and metadata filtering.Last updated -13374Apache 2.0
- -security-license-qualityA local server that provides powerful code analysis and search capabilities for software projects, helping AI assistants and development tools understand codebases for tasks like code generation and refactoring.Last updated -4
- -security-license-qualityHTTP-based server that provides semantic code search capabilities to IDEs through the Model Context Protocol, allowing efficient codebase exploration without repeated indexing.Last updated -2084
- -security-license-qualityAn intelligent server that provides semantic code search, domain-driven analysis, and advanced code understanding for large codebases using LLMs and vector embeddings.Last updated -5MIT License