CodeAlive
@CodeAlive-AI
About 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.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"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"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
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.
Frequently asked questions
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](https://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.
Basic information
More Memory & Knowledge MCP servers
MCP Apple Notes
RafalWilinskiTalk with your notes in Claude. RAG over your Apple Notes using Model Context Protocol.
Ultimate Google Docs & Drive MCP Server
a-bonusThe Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.
Zettelkasten MCP Server
entanglrA Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.
Solomd
zhitongblogA markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
Groundwork
Rarefied-EarthGroundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
Comments