MCP Catalogs
Home

metashape-mcp vs everything

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

metashape-mcp
by jenkinsm13
everything
by modelcontextprotocol
Stars★ 21★ 85,748
30d uses
Score4577
Official
Categories
Developer ToolsAI / LLM ToolsMedia
Developer ToolsAI / LLM ToolsOther
LanguagePythonTypeScript
Last committhis monththis month

metashape-mcp · Summary

MCP server providing 106 tools for Agisoft Metashape photogrammetry automation through natural language.

everything · Summary

Official MCP test server exercising all protocol features for client builders.

metashape-mcp · Use cases

  • Automating drone survey processing: import photos, align cameras, build dense clouds, generate DEMs and orthomosaics
  • Close-range 3D reconstruction: object scanning, artifact digitization, heritage documentation
  • Terrain and surface modeling: ground classification, mesh generation, texture mapping
  • Batch processing of photogrammetry projects with GCP and marker workflows
  • Headless automated processing on remote servers or CI pipelines

everything · Use cases

  • Testing MCP client implementations against all protocol features
  • Learning MCP protocol capabilities through a reference server
  • Validating client compatibility with different transport methods

metashape-mcp · Install

Installation

Prerequisites

  • Agisoft Metashape Professional 2.3+ (with Python 3.12 scripting)

Steps

  1. Clone the repository:
git clone https://github.com/jenkinsm13/metashape-mcp.git
  1. Start the MCP server inside Metashape:

- **Auto-start (recommended)**: Edit scripts/start_mcp_server.py to set the source path, copy to Metashape's scripts folder, and restart Metashape - **Manual**: Run Tools > Run Script and select scripts/start_mcp_server.py - **Console**: Open Python console and run from metashape_mcp.server import start_background; start_background() - **Headless**: Use scripts/start_mcp_headless.py for remote/CI environments

  1. Install FastMCP in your Claude Code Python:
python -c "import sys; print(sys.executable)"
pip install "fastmcp>=2.0.0"
  1. For Claude Code, configure the stdio proxy:
python proxy.py

Claude Desktop Configuration

{
  "mcpServers": {
    "metashape": {
      "command": "python",
      "args": ["path/to/proxy.py"],
      "env": {
        "METASHAPE_MCP_PORT": "8765"
      }
    }
  }
}

everything · Install

NPX (recommended)

{
  "mcpServers": {
    "everything": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-everything"]
    }
  }
}

On Windows, use cmd /c:

{
  "mcpServers": {
    "everything": {
      "command": "cmd",
      "args": ["/c", "npx", "-y", "@modelcontextprotocol/server-everything"]
    }
  }
}

Docker

{
  "mcpServers": {
    "everything": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "mcp/everything"]
    }
  }
}

Global install

npm install -g @modelcontextprotocol/server-everything@latest
npx @modelcontextprotocol/server-everything
Comparison generated from public README + GitHub signals. Last updated automatically.