By jenkinsm13
Control Agisoft Metashape photogrammetry workflows from an AI assistant — set up projects, run alignment and dense reconstruction, generate DEMs/orthos/tiled models, diagnose quality issues, and export terrain to game engines.
Diagnoses alignment failures and poor results in Metashape. When alignment rates are low, cameras fail to align, reprojection errors are high, or drift is detected, this agent investigates the cause and prescribes specific fixes. Not a QA checker (that's photogrammetry-qa) — this is the troubleshooter you call when something is already wrong.
Advises on ground control point strategy for corridor photogrammetry. Analyzes drift patterns to recommend WHERE to place GCPs, how many are needed, what accuracy to set, and how to use road markings as natural control points. Also handles marker error analysis and DEM-based virtual checkpoints.
Orchestrates the Metashape-to-Blender handoff for terrain tile workflows. Handles PLY/OBJ export from Metashape, import into Blender, coordinate system verification, tile naming conventions, and validates that tiles loaded correctly with proper transforms. Bridges the gap between the two MCP servers.
Cross-references MCP tool implementations against api_reference.txt to catch parameter mismatches, wrong defaults, missing options, and incorrect enum mappings. Use after modifying tools or when auditing tool correctness.
Quality assurance reviewer for Metashape processing. Checks alignment rates, reprojection errors, tie point counts, and mesh statistics against known-good thresholds after major processing steps. Use after alignment, tie point filtering, dense reconstruction, or mesh building.
Export all available products from the current Metashape project — point cloud, model, DEM, orthomosaic, tiled model, report, and cameras. Skips unavailable products automatically.
Orchestrate incremental alignment of long road corridor captures with automatic drift detection and QA gates. Prevents alignment divergence by checking GPS deviation gradients and continuity between batches. Works through the Metashape MCP server.
Diagnose alignment quality issues in the current Metashape project — checks camera alignment rate, tie point density, reprojection error, and sensor calibration. Provides actionable fix recommendations.
Scaffold a new Metashape MCP tool with correct imports, registration, progress tracking, and auto-save patterns. Use when adding new tools to the metashape-mcp server.
Look up Metashape Python API parameters and enums from local reference files when building or fixing MCP tools. Use when you need to verify parameter names, types, defaults, or enum values for Metashape API calls.
Admin access level
Server config contains admin-level keywords
Modifies files
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Hook triggers on file write and edit operations
Hook triggers on file write and edit operations
A comprehensive Model Context Protocol (MCP) server that brings AI-powered automation to Agisoft Metashape Professional. 106 tools, 10 resources, and 6 prompts covering the full photogrammetry pipeline — from photo alignment to 3D model export — using natural language through Claude, Claude Code, or any MCP-compatible AI assistant.
Use AI to process drone surveys, build 3D models, generate DEMs, create orthomosaics, and export production-ready deliverables — all through conversation.
This MCP server runs embedded inside Metashape's Python environment and exposes the entire photogrammetry processing pipeline as AI-callable tools. Instead of manually clicking through menus, you describe what you want and the AI executes the full workflow:
http://127.0.0.1:8765, port is user-configurable via startup script or METASHAPE_MCP_PORT env)| Module | Tools | Capabilities |
|---|---|---|
| project | 12 | Create, open, save projects; manage/merge/align/duplicate chunks; GPU/CPU config; processing status |
| photos | 5 | Import photos and video frames, analyze image quality, remove/rename cameras |
| camera | 8 | Enable/disable/select cameras, configure sensors, import/clear masks, camera metadata and reference |
| alignment | 6 | Structure-from-Motion (SfM): match photos, align cameras, optimize, filter tie points, reset alignment |
| dense | 12 | Multi-View Stereo (MVS): depth maps, dense point cloud, ground classification, filtering, smoothing, colorization |
| mesh | 8 | 3D mesh generation, decimation, smoothing, hole closing, mesh refinement, cleaning, colorization |
| texture | 5 | UV mapping, texture atlas generation, color calibration, texture removal |
| survey | 8 | DEM generation, orthomosaic creation, tiled models, contour lines, panoramas, raster export |
| export | 10 | Export to OBJ, PLY, FBX, LAS/LAZ, GeoTIFF, Cesium 3D Tiles, cameras, reference, report, and more |
| import | 6 | Import models, point clouds, reference data, camera calibrations, shapes, masks |
| markers | 9 | Detect coded markers, add/remove GCPs, create/remove scalebars, set reference, import/export markers |
| coordinate | 8 | Set CRS (EPSG codes), define bounding region, update coordinate transform, reprojection, localization |
| network | 5 | Network processing: connect, batch submit, list, monitor, abort |
| viewport | 3 | Capture viewport screenshots, read console output, auto-save project |
| scripting | 1 | Execute arbitrary Python code inside Metashape's environment |
MCP server with 295+ tools for DaVinci Resolve scripting API (v20.3) plus skills for preflight QC, color grading, delivery, Dolby Vision, timeline management, and more.
MCP server + agents/skills for Blender 5.1+ — scene management, mesh operations, import/export, and photogrammetry terrain processing.
AI-powered video editing assistant using Gemini + DaVinci Resolve. Analyzes footage, plans edits, and builds timelines automatically.
npx claudepluginhub jenkinsm13/claude-plugins --plugin metashape-mcpGeoAI-powered skills for Claude Code: inspect geospatial files, download satellite imagery, search STAC catalogs, fetch Overture Maps data, process rasters, run AI object detection, and search session logs.
Claude Code plugin for ComfyUI — generate images, visualize workflows, manage models, and explore custom nodes
Comprehensive skill for Adobe Substance 3D Painter texturing and material creation workflow. Use this skill when creating PBR materials, exporting textures for web/game engines, optimizing 3D assets for real-time rendering, or automating texture workflows. Triggers on tasks involving Substance 3D Painter, PBR texturing, material creation, texture export for Three.js, Babylon.js, Unity, Unreal, glTF optimization, or Python API automation. Creates optimized textures for threejs-webgl, react-three-fiber, and babylonjs-engine materials.
AI-powered 3D globe control for Claude Code — load tilesets, fly to locations, style layers, and query spatial data with natural language
MCP server for intelligent photo management with Immich — interactive HTML galleries with Cowork Actions Panel, geographic album curation, library cleanup, duplicate detection, people & face management, trash management, metadata repair, and 36 MCP tools. The first MCP server for self-hosted photo management.
Build high-quality datasets and computer vision models. Visualize datasets, analyze models, find duplicates, run inference, evaluate predictions, and develop custom plugins.