MCP.so
登录
C

Cocoindex Code

@cocoindex-io

代码仓库

关于 Cocoindex Code

An MCP (Model Context Protocol) server for indexing and querying codebases using CocoIndex. Features semantic code search with natural language queries, incremental indexing for fast updates, multi-language support (Python, JavaScript/TypeScript, Rust, Go, Java, C/C++, C#, SQL, S

#code-search#semantic-search#codebase#indexing#embeddings#multi-language#sqlite#cocoindex#developer-tools

基本信息

分类

开发工具

传输方式

stdio

发布者

cocoindex-io

提交者

Linghua

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "cocoindex-code": {
      "command": "uvx",
      "args": [
        "--prerelease=explicit",
        "--with",
        "cocoindex>=1.0.0a13",
        "cocoindex-code@latest"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Cocoindex Code?

Cocoindex Code is an MCP (Model Context Protocol) server for indexing and querying codebases using CocoIndex. It provides semantic code search via natural language queries, supports incremental indexing, multiple programming languages, and flexible embedding models with portable SQLite storage.

How to use Cocoindex Code?

Install uv, then add the server via claude mcp add cocoindex-code using uvx. Optionally set COCOINDEX_CODE_EMBEDDING_MODEL and the corresponding API key environment variable. The server exposes a single search tool. Configuration can be adjusted via environment variables like COCOINDEX_CODE_ROOT_PATH.

Key features of Cocoindex Code

  • Semantic code search using natural language queries
  • Incremental indexing – only re-indexes changed files
  • Multi-language support (Python, JS/TS, Rust, Go, Java, C/C++, C#, SQL, Shell, and more)
  • Local SentenceTransformers or 100+ cloud embedding providers via LiteLLM
  • Portable SQLite storage – no external database required

Use cases of Cocoindex Code

  • Find relevant code snippets by describing them in natural language
  • Rapidly navigate large, unfamiliar codebases
  • Integrate semantic code search into AI-assisted coding tools
  • Support polyglot projects with a single indexing pipeline

FAQ from Cocoindex Code

How do local embeddings differ from cloud embeddings?

Local embeddings use SentenceTransformers and require no API key; cloud embeddings use LiteLLM and need a provider API key and model identifier.

What are the runtime dependencies?

The server requires uv to run via uvx. No external database setup is needed – the index is stored locally in .cocoindex_code/.

Where is the index stored?

The index resides in .cocoindex_code/ under the codebase root, containing a vector database (target_sqlite.db) and CocoIndex state (cocoindex.db/).

Which file types are supported?

Python, JavaScript, TypeScript, Rust, Go, Java, C, C++, C#, SQL, Shell, Markdown, and Plain Text. Common generated directories are automatically excluded.

How is the codebase root discovered?

If COCOINDEX_CODE_ROOT_PATH is not set, the server looks for the nearest parent containing .cocoindex_code/, then .git/, and finally falls back to the current working directory.

评论

开发工具 分类下的更多 MCP 服务器

Grafana MCP server

grafana

MCP server for Grafana

3.2K

Test

x1xhlol

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sou

141.7K

MCP-Scan: An MCP Security Scanner

invariantlabs-ai

Security scanner for AI agents, MCP servers and agent skills.

2.8K

sentry-mcp

getsentry

An MCP server for interacting with Sentry via LLMs.

754

TalkToFigma

sonnylazuardi

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

6.9K