repo-graph gives LLMs a map of your codebase — entities, relationships, and flows — so they can navigate to the right files without reading
Repo Graph MCP server exists for a simple reason — assistants are far more useful when they can act on Repo Graph directly instead of describing what you should do. repo-graph gives LLMs a map of your codebase — entities, relationships, and flows — so they can navigate to the right files without reading everything first.
Once Repo Graph is connected, these are the calls the assistant has available:
orient — seed (optional), full, budgetfind — query, expand, kind, top_k, budgetimpact — nodes (comma-separated), direction, depth, live_only, top_k, budgettrace — from_node, to_node (optional), depth, budgetread — node (comma-separated), context_lines, budgetrefresh — repo_path (optional), fullmcp-repo-graph on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Repo Graph's toolset — orient, find, impact and 3 more — is a fair guide to whether it matches your workflow. It is maintained by james-chahwan; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| orient | seed *(optional)*, full, budget |
| find | query, expand, kind, top_k, budget |
| impact | nodes *(comma-separated)*, direction, depth, live_only, top_k, budget |
| trace | from_node, to_node *(optional)*, depth, budget |
| read | node *(comma-separated)*, context_lines, budget |
| refresh | repo_path *(optional)*, full |
{
"mcpServers": {
"repo-graph": {
"command": "uvx",
"args": ["mcp-repo-graph"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.