ultimate_mcp_server vs beanquery-mcp

Side-by-side comparison to help you pick between these two MCP servers.

	ultimate_mcp_server by Dicklesworthstone	beanquery-mcp by vanto
Stars	★ 149	★ 46
30d uses	—	—
Score	85	36
Official	—	—
Categories	AI / LLM ToolsBrowser AutomationFile System	FinanceAI / LLM ToolsDeveloper Tools
Language	Python	Python
Last commit	2 mo ago	14 mo ago

ultimate_mcp_server · Summary

Comprehensive MCP server providing dozens of capabilities for AI agents including LLM delegation, browser automation, document processing, and cognitive memory systems.

beanquery-mcp · Summary

Experimental MCP server for AI assistants to query Beancount financial ledgers using BQL.

ultimate_mcp_server · Use cases

Complex document processing and analysis with OCR and structured data extraction
Web automation and research across multiple sites with browser control
Cost-optimized AI workflows through intelligent task delegation between models

beanquery-mcp · Use cases

AI assistants analyzing personal finance patterns from Beancount ledgers
Automated financial report generation using BQL queries
Integration of financial data with other AI-powered productivity tools

ultimate_mcp_server · Install

Installation

Clone the repository:

git clone https://github.com/Dicklesworthstone/ultimate_mcp_server.git
cd ultimate_mcp_server

Install dependencies:

pip install -e .

For Claude Desktop integration, add to your claude_desktop_config.json:

{
  "mcpServers": {
    "ultimate-mcp": {
      "command": "python",
      "args": ["-m", "ultimate_mcp_server"],
      "env": {
        "PYTHONPATH": "."
      }
    }
  }
}

Run the server:

python -m ultimate_mcp_server

beanquery-mcp · Install

Installation

Prerequisites

Python 3.10 or later
[uv](https://docs.astral.sh/uv/) for managing Python projects

Running the Server

**Development Mode:**

mcp dev server.py

**Claude Desktop Integration:**

uv run mcp install server.py --with beancount --with beanquery

With environment variable:

uv run mcp install server.py -v BEANCOUNT_LEDGER=/path/to/your/ledger.bean --with beancount --with beanquery

In Claude Desktop configuration:

{
  "mcpServers": {
    "beancount": {
      "command": "uv",
      "args": ["run", "mcp", "install", "server.py"],
      "env": {
        "BEANCOUNT_LEDGER": "/path/to/your/ledger.bean"
      }
    }
  }
}

Comparison generated from public README + GitHub signals. Last updated automatically.