From metashape-mcp
Looks up Metashape Python API parameters, types, defaults, and enums from local reference files when building or fixing MCP tools.
How this skill is triggered — by the user, by Claude, or both
Slash command
/metashape-mcp:metashape-api-lookupThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When working on metashape-mcp tools, always verify API parameters against the local reference files rather than guessing.
When working on metashape-mcp tools, always verify API parameters against the local reference files rather than guessing.
The project contains these Metashape API references:
| File | Contents | When to Use |
|---|---|---|
api_reference.txt | Full Python API reference (text, searchable) | Primary reference for parameter names, types, defaults |
metashape_python_api_2_3_0.pdf | Official PDF API docs | Backup if text version is unclear |
metashape-pro_2_3_en.pdf | Metashape Pro user manual | For understanding workflow context and UI equivalents |
usgs_ofr20211039.pdf | USGS photogrammetry best practices | For filtering thresholds and workflow order |
When implementing or modifying an MCP tool:
Search api_reference.txt first — Use Grep to find the exact method signature:
Grep for: "chunk.buildModel" or "buildModel" or "Chunk.buildModel"
Check parameter types — Metashape uses its own enum types. Verify which enum a parameter expects:
Grep for: "SurfaceType" or "DataSource" or the specific enum class
Check utils/enums.py — See if the string-to-enum mapping already exists. If not, add it.
Verify defaults — The MCP tool defaults should match best-practice defaults, which may differ from Metashape API defaults. Example:
keep_keypoints: Metashape default=False, MCP default=True (required for incremental alignment)blending_mode: Use "natural" for best quality, not necessarily the API defaultThese are verified facts from the API reference — do NOT guess these:
| Topic | Correct Answer |
|---|---|
alignChunks method param | Plain int (0=tiepoints, 1=markers, 2=cameras), NOT an enum |
RasterFormatTiles | IS the correct enum for GeoTIFF export — there is no RasterFormatGeoTIFF |
face_count param | Use Metashape.CustomFaceCount with face_count_custom=0 for unlimited |
cam.meta["key"] | Bracket access only — MetaData is C++ object, no .get() method |
chunk.tie_points.points | Can be None — always check before len() |
classifyGroundPoints | On chunk.point_cloud, NOT on chunk directly |
exportRaster | Handles both DEM and orthomosaic (use source_data parameter) |
progress callback | Callable[[float], bool] — return True to continue, raise to cancel |
When adding a new tool or parameter:
api_reference.txtenums.pynpx claudepluginhub jenkinsm13/claude-plugins --plugin metashape-mcpScaffolds Metashape MCP tool modules with imports, registration, progress tracking, auto-save, prerequisite checks, and conventions. Use when adding tools to metashape-mcp server.
Generates API references, configuration guides, schema documentation, and technical references with parameter details, examples, and cross-references.
Looks up the public API of installed Python packages via introspection (inspect, pydoc, dir) and web search, caching results to avoid memory-based errors. Useful when writing code that depends on a library's exact API.