How do I install Document Analysis Engine MCP Server?

Follow the setup instructions on the Document Analysis Engine GitHub repository, then add the server configuration to your AI client.

What category is Document Analysis Engine MCP Server?

Document Analysis Engine is categorized under Knowledge & Memory. Browse more servers in these categories on MCPgee.

Document Analysis Engine

Name: Aleph
Author: Hmbown

v1.0.0•Knowledge & Memory•stable

Enables AI assistants to analyze documents larger than their context window by loading files into RAM and querying them via search, navigation, and Python execution tools. Supports recursive reasoning to process massive datasets in chunks using sub-a

llmmcprecursivereplrlm

202

Stars

Downloads

Weekly

0/5

View on GitHub

What is Document Analysis Engine?

Document Analysis Engine is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to analyze documents larger than their context window by loading files into ram and querying them via search, navigation, and python execution tools. supports recursive reasoning...

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

Enables AI assistants to analyze documents larger than their

Use Cases

Query documents larger than context window

Search and navigate massive datasets

Execute Python on document content

Hmbown

Maintainer

LicenseMIT License

Languagepython

Versionv1.0.0

UpdatedMay 19, 2026

Statushealthy

Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

View Source Browse All Servers

Installation

Manual Installation

npx aleph

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms

ThroughputMedium

Resource Usage

Memory UsageLow

CPU UsageLow

How to Set Up and Use Document Analysis Engine

Aleph (aleph-rlm) is an MCP server that loads large files and entire codebases into RAM and exposes them to AI assistants through a rich set of search, navigation, and Python execution tools — enabling analysis of documents far larger than any model's context window. It supports recursive sub-agent reasoning, where a host model can delegate deep analysis tasks to a nested backend model running locally via llama.cpp or through cloud APIs, and results persist across sessions via save/load. Data scientists, security researchers, and developers use it to query massive log files, large codebases, or multi-gigabyte datasets without chunking data manually.

Prerequisites

Python 3.10 or higher
pip or pipx for installation
An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code CLI
Optional: a running llama.cpp server and GGUF model file for local nested inference
Optional: OpenAI-compatible API key (ALEPH_SUB_QUERY_API_KEY) for cloud-based nested reasoning

Install aleph-rlm with MCP support

Install the package with the [mcp] extra to include the MCP server dependencies.

pip install "aleph-rlm[mcp]"

Run the automated installer

Use the built-in installer to automatically configure your MCP client. Choose the profile that matches your setup: 'claude' for Claude CLI, 'cursor' for Cursor, or 'portable' for no nested backend.

aleph-rlm install --profile claude
# For Cursor:
# aleph-rlm install cursor
# For project-level Cursor config:
# aleph-rlm install cursor-project

Verify the installation

Run the doctor command to check that all dependencies are present and the server can start correctly.

aleph-rlm doctor

Optional: configure a local llama.cpp backend

For fully offline recursive reasoning, set the ALEPH_PROVIDER and related variables to point at your local llama.cpp server and model file.

export ALEPH_PROVIDER=llamacpp
export ALEPH_LLAMACPP_URL=http://localhost:8080
export ALEPH_LLAMACPP_MODEL=/path/to/your/model.gguf
export ALEPH_LLAMACPP_CTX=16384

Optional: restrict to read-only mode

Set ALEPH_ACTION_POLICY=read-only to prevent Python execution tools from writing files or making network calls. Useful when analyzing untrusted documents.

export ALEPH_ACTION_POLICY=read-only

Load a large file and start querying

Once configured, ask Claude to load a file into Aleph memory and then search or analyze it. The file stays in RAM for the session.

Document Analysis Engine Examples

Client configuration

Claude Desktop configuration for Aleph using the portable profile (no nested backend).

{
  "mcpServers": {
    "aleph": {
      "command": "aleph-rlm",
      "args": [],
      "env": {
        "ALEPH_ACTION_POLICY": "read-only"
      }
    }
  }
}

Prompts to try

Example prompts for analyzing large documents and datasets with Aleph.

- "Load /var/log/syslog into Aleph and search for all ERROR entries from the last hour"
- "Load the entire src/ directory into Aleph and find all functions that call the database connection"
- "Load this 500 MB CSV file and use Python to calculate the mean and standard deviation of the 'revenue' column"
- "Search the loaded codebase for any usage of deprecated API calls and list the file names and line numbers"
- "Save the current Aleph session so I can resume this analysis tomorrow"

Troubleshooting Document Analysis Engine

aleph-rlm command not found after pip install

Ensure pip's script directory is in your PATH. Run 'python -m aleph_rlm' as a fallback, or install with pipx for automatic PATH management: 'pipx install aleph-rlm[mcp]'.

Out of memory errors when loading very large files

Aleph loads files into RAM, so ensure your system has sufficient free memory before loading very large datasets. Use 'chunk_context' and 'peek_context' tools to navigate large files in segments rather than loading everything at once.

Local llama.cpp backend fails to connect

Verify llama.cpp server is running with 'curl http://localhost:8080/health'. Check ALEPH_LLAMACPP_URL matches the server's host and port, and that ALEPH_LLAMACPP_MODEL points to a valid GGUF file path.

Frequently Asked Questions about Document Analysis Engine

What is Document Analysis Engine?

Document Analysis Engine is a Model Context Protocol (MCP) server that enables ai assistants to analyze documents larger than their context window by loading files into ram and querying them via search, navigation, and python execution tools. supports recursive reasoning to process massive datasets in chunks using sub-a It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Document Analysis Engine?

Follow the installation instructions on the Document Analysis Engine GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Document Analysis Engine?

Document Analysis Engine works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Document Analysis Engine free to use?

Yes, Document Analysis Engine is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Document Analysis Engine Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Document Analysis Engine? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & Memory Browse All Servers

Set Up Document Analysis Engine in Your Editor

Choose your AI client for step-by-step setup instructions.

🖥️

Claude Desktop

macOS & Windows app

⌨️

Claude Code

CLI & terminal

📝

Cursor

AI-first code editor

💻

VS Code

GitHub Copilot MCP

🏄

Windsurf

Codeium AI editor

🔌

Cline

VS Code extension

Quick Config Preview

{
  "mcpServers": {
    "aleph": {
      "command": "npx",
      "args": ["-y", "aleph"]
    }
  }
}

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Document Analysis Engine?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides

Explore All Servers Read Our Guides