What is Doc Builder Mcp

doc-builder-mcp is a Model Context Protocol (MCP) server designed for building and querying document collections using ChromaDB, specifically optimized for ingesting large files.

Use cases

Use cases for doc-builder-mcp include ingesting large datasets for machine learning, managing document collections in research environments, and integrating with applications that require document retrieval and processing.

How to use

To use doc-builder-mcp, install it via pip with ‘pip install -e .’, then run the server with ‘uv run main.py --chroma-path /path/to/storage/directory’ to enable persistent storage.

Key features

Key features include automatic chunking of documents during ingestion, support for various file types (text, binary, images), and the ability to return a truncated content preview along with metadata such as content type and file size.

Where to use

doc-builder-mcp can be used in fields that require efficient document management and querying, such as data analysis, content management systems, and large-scale document storage solutions.

Document Builder MCP

A Model Context Protocol (MCP) server for building and querying document collections with ChromaDB.

Features

• Ingest documents to collections with automatic chunking

Installation

uv pip install -e .

Usage

Run the MCP server:

# Run with persistent storage (required)
uv run main.py --chroma-path /path/to/storage/directory

Available Tools

File Ingestion

• ingest_file(file_path, collection_name, content_type): Read a file, chunk it, and store in ChromaDB
  • Automatically handles text files with recursive chunking
  • Supports binary and image files
  • Returns truncated content preview (100 chars), content type, file size, and chunk count

Integration with Claude

Add this server to your Claude configuration:

{
  "mcpServers": {
    "doc-builder": {
      "command": "uv run /path/to/doc_builder_mcp/main.py --chroma-path /path/to/storage/directory"
    }
  }
}

Development

Run the server in development mode with MCP Inspector:

uv run mcp dev main.py --chroma-path /path/to/dev/storage