# mcp-long-context-reader

Source: https://glimind.com/server/pypi%2Fmcp-long-context-reader
Registry id: `pypi/mcp-long-context-reader`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "mcp-long-context-reader": {
      "command": "uvx",
      "args": [
        "mcp-long-context-reader"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add mcp-long-context-reader -- uvx mcp-long-context-reader
```

## Tools (5)

- `glance`: Provides a quick look at the beginning of a file, showing the first few thousands characters and total line count.
- `retrieve_with_rag`: Uses a Retrieval-Augmented Generation (RAG) pipeline to find the most semantically relevant document chunks based on a natural language question.
- `search_with_regex`: Finds and extracts text snippets using regular expression patterns.
- `summarize_with_map_reduce`: A classic 'divide and conquer' strategy that summarizes large chunks in parallel and then combines those summaries.
- `summarize_with_sequential_notes`: An advanced strategy where an LLM reads the document sequentially, taking query-aware notes.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
