Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search.
Connect Deeprepo to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search. The deeprepo mcp server is what makes that connection.
A production-grade Python library for performing RAG (Retrieval Augmented Generation) on local codebases. No heavy frameworks, no external vector DBs, no cloud required.
The server ships on PyPI as deeprepo, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
ingest_codebase — One-time setup — index a repo directoryfind_symbol — "Where is X defined / what line is X on"get_file_structure — "Show me the API / functions in X"explain_file — "How does X work / explain X / what does X do"find_change_impact — "What breaks if I change X"ask_codebase — Any open-ended question about the codeget_project_overview — "Give me an overview / what does this project do"Examples — The Examples tool exposed by this serverStorage — Everything lives in a single SQLite file per branch — no Redis, no Postgres, no ChromaSetup — The Setup tool exposed by this serverConfiguration is passed through the environment: LLM_PROVIDER, EMBEDDING_PROVIDER, OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, HUGGINGFACE_API_KEY, OLLAMA_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of database access 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. Deeprepo's toolset — ingest_codebase, find_symbol, get_file_structure and 7 more — is a fair guide to whether it matches your workflow. It is maintained by abhishek2432001; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.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 |
|---|---|
| ingest_codebase | One-time setup — index a repo directory |
| find_symbol | "Where is X defined / what line is X on" |
| get_file_structure | "Show me the API / functions in X" |
| explain_file | "How does X work / explain X / what does X do" |
| find_change_impact | "What breaks if I change X" |
| ask_codebase | Any open-ended question about the code |
| get_project_overview | "Give me an overview / what does this project do" |
| Examples | The Examples tool exposed by this server. |
| Storage | Everything lives in a **single SQLite file per branch** — no Redis, no Postgres, no Chroma. |
| Setup | The Setup tool exposed by this server. |
{
"mcpServers": {
"deeprepo": {
"command": "uvx",
"args": ["deeprepo"],
"env": {
"LLM_PROVIDER": "your-value",
"EMBEDDING_PROVIDER": "your-value",
"OPENAI_API_KEY": "your-value",
"ANTHROPIC_API_KEY": "your-value",
"GEMINI_API_KEY": "your-value",
"HUGGINGFACE_API_KEY": "your-value",
"OLLAMA_BASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| LLM_PROVIDER | Configuration value read at startup. | Optional |
| EMBEDDING_PROVIDER | Configuration value read at startup. | Optional |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
| HUGGINGFACE_API_KEY | Credential the server authenticates with. | Yes |
| OLLAMA_BASE_URL | Endpoint or connection string the server talks to. | Yes |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.