CodeAlive

Name: CodeAlive
Author: CodeAlive-AI

@CodeAlive-AI

关于 CodeAlive

Provides a bridge to CodeAlive's platform for semantic code search, repository exploration, and context-aware chat completions that leverage deep understanding of entire codebases including documentation and dependencies.

#codealive #code-search #ai-assistant

基本信息

分类

记忆与知识

传输方式

stdio

发布者

CodeAlive-AI

提交者

Ivan Biruk

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "codealive": {
      "command": "/path/to/your/codealive-mcp/.venv/bin/python",
      "args": [
        "/path/to/your/codealive-mcp/src/codealive_mcp_server.py",
        "--debug"
      ],
      "env": {
        "CODEALIVE_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

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 CodeAlive?

CodeAlive is an MCP (Model Context Protocol) server that connects AI clients (such as Claude Desktop, Cursor, VS Code with GitHub Copilot, Continue, Cline, Roo-Code, and Refact) to the CodeAlive platform. CodeAlive analyzes your entire codebase—including documentation and dependencies—and builds a detailed internal map of structure, patterns, and logic. This server enriches AI agents with deep, semantic code context, enabling faster, more accurate answers and reduced token‑wasting file searches.

How to use CodeAlive?

Clone the repository, set up a Python 3.11 virtual environment with uv (recommended) or pip, and install the package (uv pip install -e .). Obtain a CodeAlive API key from your account at app.codealive.dev. Configure the server in your AI client (e.g., Claude Desktop JSON, Cursor MCP settings) by providing the command, script path, and the API key via the CODEALIVE_API_KEY environment variable or the --api-key CLI flag. Use --transport stdio (default) or --transport sse, and optionally --debug for verbose logging.

Key features of CodeAlive

Semantic code search across all indexed datasources.
Chat completions enriched with full codebase context.
List available repositories and workspaces.
Compatible with multiple AI client integrations.
Supports both stdio and SSE transport protocols.

Use cases of CodeAlive

Quickly locate relevant code snippets related to a developer’s question.
Understand relationships and patterns across an entire repository or workspace.
Reduce AI agent costs by providing precise context, minimising file traversal.
Onboard new team members by answering “what does this code do?” with complete code context.
Debug issues by asking high‑level questions that span files and dependencies.

FAQ from CodeAlive

What AI clients can I use with CodeAlive?

The server is designed for Claude Desktop, Cursor, VS Code (GitHub Copilot), Continue, Cline, Roo-Code, and Refact.

How do I get a CodeAlive API key?

Log in to app.codealive.dev, navigate to the “API Keys” section under your Organization, click “+ Create API Key”, name it, select the desired scope, and copy the key immediately—it will not be shown again.

What are the runtime requirements?

Python 3.11, along with uv (recommended) or pip. You also need a CodeAlive account and an active API key.

What transport methods are supported?

The server supports stdio (default) and sse. For SSE you can specify --host (default 0.0.0.0) and --port (default 8000).

Where can I find troubleshooting logs?

For Claude Desktop: on macOS look in ~/Library/Logs/Claude/ (files like mcp.log and mcp-server-codealive.log); on Windows use %LOCALAPPDATA%\Claude\Logs\. For Cursor, check the Output panel (select “CodeAlive” or “MCP”) or use Developer Tools → Console.