Sourcerer Mcp

Created By

st3v3nmw4 months ago

An MCP server for semantic code search & navigation that helps AI agents work efficiently without burning through costly tokens. Instead of reading entire files, agents can search conceptually and jump directly to the specific functions, classes, and code chunks they need.

# sourcerer

# code-search

Overview Content Tools Comments

Overview

what is Sourcerer MCP?

Sourcerer MCP is a server designed for semantic code search and navigation, enabling AI agents to efficiently locate specific functions, classes, and code chunks without the need to read entire files, thus conserving costly token usage.

how to use Sourcerer MCP?

To use Sourcerer MCP, install it via Go or Homebrew, configure it with your OpenAI API key, and set up your project workspace. Once configured, you can utilize its semantic search capabilities to find relevant code snippets.

key features of Sourcerer MCP?

Semantic search index for efficient code navigation
Integration with OpenAI API for generating embeddings
Automatic re-indexing of changed files
Support for multiple programming languages (Go, with plans for Python, TypeScript, JavaScript)

use cases of Sourcerer MCP?

Assisting AI agents in quickly finding relevant code snippets.
Reducing cognitive load by allowing conceptual searches instead of text matching.
Enhancing code navigation in large codebases.

FAQ from Sourcerer MCP?

What programming languages does Sourcerer MCP support?

Currently, it supports Go, with plans to add Python, TypeScript, and JavaScript.

Do I need an OpenAI API key to use Sourcerer MCP?

Yes, an OpenAI API key is required for generating embeddings.

How does Sourcerer MCP handle file changes?

It automatically re-indexes changed files and respects .gitignore files.

Server Config

{
  "mcpServers": {
    "sourcerer": {
      "command": "sourcerer",
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key",
        "SOURCERER_WORKSPACE_ROOT": "/path/to/your/project"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

Tavily Mcp

WindsurfThe new purpose-built IDE to harness magic

Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code

Serper MCP ServerA Serper MCP Server

TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

ChatWiseThe second fastest AI chatbot™

DeepChatYour AI Partner on Desktop

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs