metashape-mcp

Overview

Metashape MCP Server integrates AI-powered automation directly into Agisoft Metashape Professional, providing comprehensive control over the entire photogrammetry pipeline. The server exposes 106 tools across 15 modules covering everything from photo alignment to 3D model export, plus 10 resources for real-time project inspection and 6 guided workflow prompts. It runs natively inside Metashape's Python environment with both HTTP and stdio transport options to handle both quick operations and long-running tasks without timeout issues.

Try asking AI

After installing, here are 8 things you can ask your AI assistant:

• create_project

  Create a new Metashape project

  Try:Create a new photogrammetry projectTry:Start a new Metashape project for processing drone photos
• import_photos

  Import photos into a Metashape project

  Try:Import these photos from the folder C:/drone_photosTry:Add images to my current project
• align_photos

  Perform structure-from-motion to align camera positions

  Try:Align the photos to create camera positionsTry:Run structure-from-motion on my imported images
• build_dense_cloud

  Generate a dense point cloud from aligned photos

  Try:Create a dense point cloud from the aligned photosTry:Generate dense point cloud for my 3D model
• build_mesh

  Generate a 3D mesh from the dense point cloud

  Try:Build a 3D mesh from my dense cloudTry:Create a surface model of the terrain
• build_texture

  Apply texture to the 3D mesh

  Try:Add texture to my 3D modelTry:Create a realistic texture for the mesh
• generate_dem

  Generate a Digital Elevation Model from the dense cloud

  Try:Create a DEM from my point cloudTry:Generate elevation data for the survey area
• create_orthomosaic

  Create an orthomosaic from the aligned photos

  Try:Create an orthomosaic of the survey areaTry:Generate a bird's-eye view map of the site
• export_model

  Export the 3D model to a specified format

  Try:Export my 3D model as an OBJ fileTry:Save the textured model in FBX format
• detect_markers

  detect coded markers in the photos

  Try:Find all the ground control points in my photosTry:Detect coded markers for georeferencing
• set_crs

  Set the coordinate reference system for the project

  Try:Set the coordinate system to EPSG:32633Try:Use UTM zone 33N for georeferencing
• execute_script

  Execute custom Python code in Metashape

  Try:Run this Python script: chunk.matchPhotos()Try:Execute custom processing code

Comparable tools

Installation

git clone https://github.com/jenkinsm13/metashape-mcp.git

python -c "import sys; print(sys.executable)"
pip install "fastmcp>=2.0.0"

python proxy.py

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

FAQ

How does this differ from using Metashape's Python API directly?

Instead of writing Python code, you describe what you want in natural language and the AI generates and executes the appropriate Metashape scripts. This makes photogrammetry processing accessible to non-programmers.

Can I run this without the Metashape GUI?

Yes. The server supports headless mode using `start_mcp_headless.py` for automated processing on remote servers, VMs, or CI/CD pipelines without a display.

What happens if an operation takes longer than 60 seconds?

The stdio proxy has no timeout limits, unlike the HTTP transport which can time out after 60 seconds. This allows long operations like dense cloud generation to run for hours without interruption.

Compare metashape-mcp with