MCP Catalogs
Home

agience-core vs ultimate_mcp_server

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

agience-core
by Agience
ultimate_mcp_server
by Dicklesworthstone
Stars★ 39★ 149
30d uses
Score4585
Official
Categories
AI / LLM ToolsKnowledge GraphDeveloper Tools
AI / LLM ToolsBrowser AutomationFile System
LanguagePythonPython
Last commit1 mo ago2 mo ago

agience-core · Summary

Agience is an MCP-native platform that structures AI outputs into durable, versioned artifacts with provenance tracking.

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.

agience-core · Use cases

  • Collaborative knowledge management where AI and humans work with the same information substrate
  • Audit trail tracking for AI-generated decisions and content in regulated industries
  • Composable AI agent workflows with structured inputs and outputs via MCP

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

agience-core · Install

Installation Options

**Run at Home (Stable Build)**

# Linux/macOS
curl -fsSL https://get.agience.ai/home/install.sh | sh

# Windows (PowerShell)
irm https://get.agience.ai/home/install.ps1 | iex

**Developer Setup (Build from Source)**

git clone https://github.com/Agience/agience-core.git
cd agience-core
# Linux/macOS
./agience dev -f --build
# Windows
agience dev -f --build

**MCP Client Configuration** For Claude Desktop, add to claude_desktop_config.json:

"mcpServers": {
  "agience": {
    "command": "python",
    "args": ["-m", "agience.mcp"]
  }
}

ultimate_mcp_server · Install

Installation

  1. Clone the repository:
git clone https://github.com/Dicklesworthstone/ultimate_mcp_server.git
cd ultimate_mcp_server
  1. Install dependencies:
pip install -e .
  1. For Claude Desktop integration, add to your claude_desktop_config.json:
{
  "mcpServers": {
    "ultimate-mcp": {
      "command": "python",
      "args": ["-m", "ultimate_mcp_server"],
      "env": {
        "PYTHONPATH": "."
      }
    }
  }
}
  1. Run the server:
python -m ultimate_mcp_server
Comparison generated from public README + GitHub signals. Last updated automatically.