# rapidbm25

> rapidbm25 is an MCP server for developer tools. Local BM25 keyword search over texts or a code and docs folder, with a Rust core. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Platforms:** CLI, Linux, macOS, Windows
- **Repository:** https://github.com/maverick0351a/rapidbm25
- **MCP Registry name:** io.github.Maverick0351a/rapidbm25
- **Categories:** [developer tools](https://ai-powered.com/categories/developer-tools), [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm)
- **Listing updated:** 2026-11-14

## About

Behind this MCP server is rapidbm25, a Rust-native stand-in for the `rank_bm25` Python classes BM25Okapi, BM25L and BM25Plus. The README claims bit-for-bit identical scores and roughly 1,470 times faster `get_scores`, and the server wraps the same engine so an agent can run keyword ranking without a network call.

The server indexes a folder through `bm25_index_path`, which is backed by a live index that supports add, delete and update without rebuilding. Two environment variables control it: `RAPIDBM25_ROOTS` limits which directories may be read (default the working directory) and `RAPIDBM25_CACHE` sets the cache folder (default `~/.cache/rapidbm25`).

The library side adds optional tokenizers with stemming and CJK bigrams, metadata filters, batch search, save and load, and reciprocal rank fusion for hybrid ranking. Prebuilt wheels cover CPython 3.9 to 3.15 on Linux, macOS and Windows.

## Features

- **Drop-in rank_bm25 scores:** Matches rank_bm25 scores exactly, with a compat option for the project's git-main behaviour.
- **Live index:** Add, delete and update documents without rebuilding posting lists.
- **Metadata filters:** Restrict searches with operators such as $eq, $in and $gt.
- **Optional tokenizers:** Unicode words, stop lists, Snowball stemming and CJK bigrams.
- **Rank fusion:** Combine several rankings with reciprocal rank fusion.

## Good for

- Search a code or docs folder by keyword from an agent
- Replace rank_bm25 in a Python pipeline for speed
- Combine keyword and vector rankings with rank fusion
- Keep an incrementally updated search index

## Install

### Claude Code (Terminal)

```sh
claude mcp add rapidbm25 -- uvx rapidbm25
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "rapidbm25": {
      "command": "uvx",
      "args": [
        "rapidbm25"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "rapidbm25": {
      "command": "uvx",
      "args": [
        "rapidbm25"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "rapidbm25": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "rapidbm25"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "rapidbm25": {
      "command": "uvx",
      "args": [
        "rapidbm25"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "rapidbm25": {
      "command": "uvx",
      "args": [
        "rapidbm25"
      ]
    }
  }
}
```

## Tools

- `bm25_index_path`: Index a folder of code or docs for BM25 keyword search

## FAQ

### Does it need a network connection?

No; the registry entry describes it as local with no network.

### Which directories can the server read?

Those listed in RAPIDBM25_ROOTS, defaulting to the working directory.

### Is it identical to rank_bm25?

Scores match bit for bit; tie order and a few edge cases differ, as documented in the README.

### How do I add rapidbm25 to Claude Code?

Run this command in your terminal: claude mcp add rapidbm25 -- uvx rapidbm25

### What are the best alternatives to rapidbm25?

The closest alternatives to rapidbm25 are rag-mcp, WARM, MiniRAG, MarkIndex and Searchcraft.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [rag-mcp](https://ai-powered.com/mcp/rag-mcp): rag-mcp is an open-source MCP server for knowledge and memory.
- [WARM](https://ai-powered.com/mcp/warm-2): WARM is an open-source MCP server for knowledge and memory.
- [MiniRAG](https://ai-powered.com/mcp/minirag): MiniRAG is an open-source MCP server for knowledge and memory.
- [MarkIndex](https://ai-powered.com/mcp/markindex): MarkIndex is an open-source MCP server for knowledge and memory.
- [Searchcraft](https://ai-powered.com/mcp/searchcraft): Searchcraft is an open-source MCP server for developer tools.
- [AsterMind MCP](https://ai-powered.com/mcp/astermind-mcp): AsterMind MCP is a free MCP server for ai models and llm tooling.
- [Open Context Engine](https://ai-powered.com/mcp/open-context-engine): Open Context Engine is an open-source MCP server for developer tools.
- [Deeprepo](https://ai-powered.com/mcp/deeprepo): Deeprepo is an open-source MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/rapidbm25
