DocSlicer

Overview

DocSlicer is a Model Context Protocol (MCP) server: Answer questions from documents too large to fit in context, reading only the sections you need. Because it speaks the Model Context Protocol, AI assistants can use DocSlicer as a set of callable tools instead of you copy-pasting between apps.

It runs locally: the Python package docslicer (via uvx) speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need DOCSLICER_MCP_ROOT. The current release is v0.2.4, published under the AGPL-3.0 license, with source at DocSlicer/DocSlicer on GitHub, where it has earned 35 stars.

On mcp.site, DocSlicer sits in the AI & Agents category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain DocSlicer for DocSlicer, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "docslicer": {
      "command": "uvx",
      "args": [
        "docslicer"
      ],
      "env": {
        "DOCSLICER_MCP_ROOT": "<docslicer-mcp-root>"
      }
    }
  }
}

Requires DOCSLICER_MCP_ROOT