AutoDev Codebase

v1.0.0Developer Toolsstable

A vector embedding-based code semantic search tool with MCP server and multi-model integration. Can be used as a pure CLI tool. Supports Ollama for fully local embedding and reranking, enabling complete offline operation and privacy protection for yo

autodev-codebase-mcp-servermcpai-integration
Share:
117
Stars
0
Downloads
0
Weekly
0/5

What is AutoDev Codebase?

AutoDev Codebase is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to vector embedding-based code semantic search tool with mcp server and multi-model integration. can be used as a pure cli tool. supports ollama for fully local embedding and reranking, enabling complete...

A vector embedding-based code semantic search tool with MCP server and multi-model integration. Can be used as a pure CLI tool. Supports Ollama for fully local embedding and reranking, enabling complete offline operation and privacy protection for yo

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A vector embedding-based code semantic search tool with MCP

Use Cases

Perform semantic code search using vector embeddings.
Work with Ollama for fully local, privacy-preserving codebase analysis.
Integrate multi-model embedding and reranking for intelligent code discovery.
anrgct

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx autodev-codebase-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use AutoDev Codebase

AutoDev Codebase is a vector-embedding-based semantic code search tool that indexes your source files into a Qdrant vector database and serves search results through an MCP server. It supports fully local, offline operation via Ollama for both embedding and reranking, which keeps proprietary code entirely on-device. Developers use it to find semantically related code across large repositories, explore call graphs, and generate AI-powered outlines — all from their MCP-compatible AI assistant.

Prerequisites

  • Node.js 18+ and npm (for the @autodev/codebase package)
  • Ollama installed and running locally (`brew install ollama` on macOS), or an OpenAI-compatible API key for cloud embeddings
  • Docker (for running the Qdrant vector database)
  • ripgrep installed (`brew install ripgrep`) for file discovery
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Install Ollama and pull an embedding model

Ollama provides local, privacy-preserving embeddings. Pull the `nomic-embed-text` model which AutoDev Codebase uses by default for offline operation.

brew install ollama
ollama serve
ollama pull nomic-embed-text
2

Start the Qdrant vector database

AutoDev Codebase stores code vectors in Qdrant. Run it locally via Docker — no configuration is needed for the default setup.

docker run -d -p 6333:6333 -p 6334:6334 --name qdrant qdrant/qdrant
3

Install the AutoDev Codebase CLI globally

Install the @autodev/codebase package globally so the `codebase` command is available system-wide.

npm install -g @autodev/codebase
4

Configure the embedding provider

Point AutoDev Codebase at your Ollama instance. You can also switch to OpenAI or other providers by setting the corresponding keys.

# Local Ollama setup
codebase config --set embedderProvider=ollama,embedderModelId=nomic-embed-text

# Or OpenAI
codebase config --set embedderProvider=openai,embedderModelId=text-embedding-3-small,embedderOpenAiApiKey=sk-your-key
5

Index your codebase and start the MCP server

Run `codebase index --serve` from your project root. This indexes all source files and starts an MCP HTTP server on port 3001 by default.

cd /path/to/your/project
codebase index --serve --port 3001

AutoDev Codebase Examples

Client configuration (Claude Desktop)

Connect to the running AutoDev Codebase MCP server over HTTP. Start the server first with `codebase index --serve`, then add this config.

{
  "mcpServers": {
    "autodev-codebase": {
      "command": "npx",
      "args": ["-y", "@autodev/codebase", "index", "--serve", "--stdio"]
    }
  }
}

Prompts to try

These prompts leverage the semantic search, call graph, and outline tools exposed by AutoDev Codebase.

- "Search the codebase for code related to user authentication."
- "Show me the call graph starting from the `main` function up to depth 5."
- "Generate an outline with AI summaries for all TypeScript files in src/."
- "Find functions semantically similar to 'database connection pooling'."
- "What code in this repo handles payment processing?"

Troubleshooting AutoDev Codebase

Embedding errors or empty search results after indexing

Verify Ollama is running (`ollama serve`) and the `nomic-embed-text` model is available (`ollama list`). Check that Qdrant is reachable on port 6333 (`curl http://localhost:6333/healthz`). Re-run `codebase index` if the database was restarted.

`codebase` command not found after npm install

Ensure npm's global bin directory is on your PATH. Run `npm bin -g` to find the path and add it to your shell profile (e.g., `export PATH=$(npm bin -g):$PATH`).

Low-quality or irrelevant search results

Increase the minimum score threshold: `codebase config --set vectorSearchMinScore=0.75`. Enable reranking for better precision: `codebase config --set rerankerEnabled=true,rerankerProvider=ollama`.

Frequently Asked Questions about AutoDev Codebase

What is AutoDev Codebase?

AutoDev Codebase is a Model Context Protocol (MCP) server that vector embedding-based code semantic search tool with mcp server and multi-model integration. can be used as a pure cli tool. supports ollama for fully local embedding and reranking, enabling complete offline operation and privacy protection for yo It connects AI assistants to external tools and data sources through a standardized interface.

How do I install AutoDev Codebase?

Follow the installation instructions on the AutoDev Codebase GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with AutoDev Codebase?

AutoDev Codebase works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is AutoDev Codebase free to use?

Yes, AutoDev Codebase is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "autodev-codebase-mcp-server": { "command": "npx", "args": ["-y", "autodev-codebase-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use AutoDev Codebase?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides