# Sourcegraph

> Use this tool when you need to efficiently explore and search large codebases across multiple repositories. It solves problems related to code discovery, exploration, and understanding by providing advanced code search, intelligent query guidance, and content fetching capabilities. With support for regex patterns, language filters, and repository scoping, it offers a powerful interface for retrieving file contents, directory structures, and constructing effective search queries.

Canonical page: https://skillsregistry.net/skills/divar-sourcegraph  
JSON: https://api.skillsregistry.net/v1/skills/divar-sourcegraph

## Description

The Sourcegraph MCP Server by Divar provides AI assistants with powerful code search and repository exploration capabilities through Sourcegraph's search API. It offers three core tools: advanced code search with support for regex patterns, language filters, and repository scoping; intelligent search query guidance that helps construct effective Sourcegraph queries; and content fetching for retrieving file contents or directory structures from repositories. The implementation uses FastMCP with both SSE and HTTP transports, includes comprehensive prompt management through YAML templates, and supports both public and authenticated Sourcegraph instances, making it valuable for code discovery, codebase exploration, and understanding large software projects across multiple repositories.

## Trust

- **Trust score (0–1):** 0.76
- **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/divar-sourcegraph)
- **Repository:** <https://github.com/najva-ai/sourcegraph-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": "divar-sourcegraph"
    }
  }
}
```

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