# Sourcerer

> Use this tool when you need to search and analyze Go codebases semantically, or when exploring unfamiliar code, conducting code reviews, or building AI-assisted development tools. It takes in natural language queries and Go source files, and outputs relevant code sections, formatted code chunks, and summaries. This tool is ideal for developers seeking to understand complex code structures and relationships, and provides accurate results through Tree-sitter parsing and vector embeddings.

Canonical page: https://skillsregistry.net/skills/st3v3nmw-sourcerer  
JSON: https://api.skillsregistry.net/v1/skills/st3v3nmw-sourcerer

## Description

This MCP server provides semantic code search and analysis for Go codebases using Tree-sitter parsing and vector embeddings, built by Stephen Mwangi with chromem-go for vector storage and real-time file watching capabilities. The implementation indexes Go source files into semantic chunks (functions, methods, types) with automatic staleness detection and background re-indexing, offering two core tools: semantic search that finds relevant code sections using natural language queries, and source code retrieval that returns formatted code chunks with line numbers and summaries. Features include Tree-sitter-based AST parsing for accurate code structure extraction, file system watching with debounced updates for active development workflows, and persistent vector storage that maintains search indexes across sessions, making it valuable for developers exploring unfamiliar codebases, conducting code reviews, or building AI-assisted development tools that need contextual code understanding.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/st3v3nmw-sourcerer)
- **Repository:** <https://github.com/st3v3nmw/sourcerer-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "st3v3nmw-sourcerer"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/st3v3nmw-sourcerer` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/st3v3nmw-sourcerer/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt