// SCAN REPORT

Metashape MCP Server

112 tools. 92 can modify or destroy data without limits.

15 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

92 can modify or destroy data

20 read-only

112 tools total

Community server · catalogue entry verified 11/06/2026

How to control Metashape MCP Server ↓

TOOL MAP

What Metashape MCP Server exposes to your agents

Read (20) Write / Execute (75) Destructive / Financial (15)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Metashape MCP Server tools

Destructive · High reset_camera_alignment This tool permanently deletes camera alignment data, which represents processed photogrammetry results that cannot be recovered without re-running the alignment process. Destructive · High clean_model Removing artifacts from a model is a destructive operation because it permanently deletes portions of the 3D model data. Destructive · High clear_dem The tool permanently deletes the DEM (Digital Elevation Model), which represents processed 3D terrain data that cannot be recovered without re-running computationally expensive photogrammetry operations. Destructive · High clear_depth_maps The tool permanently deletes depth maps, which are valuable intermediate computational products in a photogrammetry workflow.

92 of Metashape MCP Server's 112 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Metashape MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Metashape MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clean_model": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "reset_region": {
    "limits": [
      {
        "counter": "reset_region_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_images": {
    "limits": [
      {
        "counter": "analyze_images_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Metashape MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON METASHAPE →

Free to start. No card required.

FULL CATALOGUE

All 112 Metashape MCP Server tools

DESTRUCTIVE 15 tools

Destructive clean_model Remove model artifacts based on filtering criteria. Destructive clear_dem Remove the DEM from the active chunk to free memory. Destructive clear_depth_maps Remove depth maps from the active chunk to free memory. Destructive clear_masks Remove masks from cameras. Destructive clear_model Remove the 3D model from the active chunk to free memory. Destructive clear_orthomosaic Remove the orthomosaic from the active chunk to free memory. Destructive clear_point_cloud Remove the dense point cloud from the active chunk to free memory. Destructive clear_tiled_model Remove the tiled model from the active chunk to free memory. Destructive remove_cameras remove_cameras Destructive remove_marker Remove a marker by its label. Destructive remove_points_by_class remove_points_by_class Destructive remove_scalebar Remove a scalebar by its label. Destructive remove_texture Remove texture from the model but keep the mesh geometry. Destructive reset_camera_alignment Clear all camera alignment data from the active chunk. Destructive network_abort_batch Abort a running network batch.

EXECUTE 18 tools

Execute cancel_processing Cancel the currently running Metashape operation. Execute build_contours build_contours Execute build_dem build_dem Execute build_depth_maps build_depth_maps Execute build_model build_model Execute build_orthomosaic build_orthomosaic Execute build_panorama build_panorama Execute build_point_cloud Build a dense point cloud from depth maps. Execute build_texture build_texture Execute build_tiled_model build_tiled_model Execute build_uv build_uv Execute execute_python execute_python Execute align_cameras align_cameras Execute align_chunks Align chunks relative to each other. Execute calibrate_reflectance calibrate_reflectance Execute match_photos match_photos Execute network_connect Connect to a Metashape network processing server. Execute network_submit_batch network_submit_batch

WRITE 57 tools

Write reset_region Reset the processing region to automatically fit all chunk data. Write transform_chunk_crs Reproject the chunk to a new coordinate reference system. Write add_chunk Add a new chunk to the project. Write add_marker Add a marker manually to the active chunk. Write add_photos Add photos to the active chunk. Write add_scalebar add_scalebar Write assign_point_class Reclassify points from one class to another. Write auto_save Save the project to its current path. Write calculate_point_normals calculate_point_normals Write calibrate_colors calibrate_colors Write classify_ground_points classify_ground_points Write close_holes Close holes in the 3D mesh. Write colorize_point_cloud Colorize the dense point cloud from source imagery. Write create_project Create a new empty Metashape project. Write create_shape create_shape Write decimate_model Reduce mesh complexity by decimating to a target face count. Write duplicate_chunk duplicate_chunk Write enable_cameras enable_cameras Write export_dem Export the DEM to a raster file. Write export_markers Export all marker positions to file. Write export_model export_model Write export_orthomosaic Export the orthomosaic to a raster file. Write export_point_cloud export_point_cloud Write export_reference Export camera reference data (positions and errors) to file. Write export_report Export a processing report in PDF format. Write export_shapes export_shapes Write export_tie_points export_tie_points Write export_tiled_model Export a tiled model for web/3D streaming. Write filter_point_cloud filter_point_cloud Write filter_points_by_confidence filter_points_by_confidence Write filter_tie_points filter_tie_points Write import_cameras Import camera positions and orientations from file. Write import_masks import_masks Write import_model import_model Write import_point_cloud import_point_cloud Write import_reference import_reference Write import_shapes import_shapes Write import_video import_video Write merge_chunks merge_chunks Write open_project Open a Metashape project file (.psx/.psz). Write optimize_cameras optimize_cameras Write refine_markers Refine marker positions for sub-pixel accuracy. Write refine_model refine_model Write rename_cameras rename_cameras Write save_project Save the current project. Write select_cameras select_cameras Write set_active_chunk Switch the active chunk by label or index. Write set_camera_reference set_camera_reference Write set_crs set_crs Write set_gpu_config set_gpu_config Write set_marker_reference set_marker_reference Write set_reference_settings set_reference_settings Write set_region set_region Write set_region_rotation set_region_rotation Write set_sensor set_sensor Write smooth_model smooth_model Write update_transform Update the chunk transformation matrix.

READ 20 tools

Read analyze_images analyze_images Read check_alignment_continuity check_alignment_continuity Read detect_markers detect_markers Read get_alignment_stats Return detailed alignment quality metrics for the active chunk. Read get_camera_metadata Return detailed metadata for a specific camera. Read get_camera_spatial_stats get_camera_spatial_stats Read get_chunk_bounds Return the bounding box of the chunk's data in geographic coordinates. Read get_console_output Read the Metashape console pane output. Read get_corridor_drift_report get_corridor_drift_report Read get_model_stats Return detailed statistics about the current 3D model. Read get_point_cloud_stats Return dense point cloud statistics. Read get_processing_status get_processing_status Read get_reprojection_error_by_region get_reprojection_error_by_region Read list_chunks List all chunks in the project with summary info. Read list_markers List all markers with their coordinates and error estimates. Read list_sensors List all sensors in the active chunk with calibration details. Read network_batch_status Get detailed status of a network batch. Read network_list_batches List all batches on the network server. Read compare_alignment_to_dem compare_alignment_to_dem Read export_cameras Export camera positions and orientations.

OTHER 2 tools

Other capture_viewport capture_viewport Other generate_virtual_checkpoints generate_virtual_checkpoints

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Metashape MCP Server

Can an AI agent delete data through the Metashape MCP Server MCP server? +

Yes. The Metashape MCP Server server exposes 15 destructive tools including clean_model, clear_dem, clear_depth_maps. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Metashape MCP Server? +

The Metashape MCP Server server has 57 write tools including reset_region, transform_chunk_crs, add_chunk. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Metashape MCP Server.

How many tools does the Metashape MCP Server MCP server expose? +

112 tools across 4 categories: Destructive, Execute, Read, Write. 20 are read-only. 92 can modify, create, or delete data.

How do I enforce a policy on Metashape MCP Server? +

Register the Metashape MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Metashape MCP Server tool call.

Deterministic rules across all 112 Metashape MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON METASHAPE →

Free to start. No card required.

112 Metashape MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.