# Reconstruct a textured 3D object from overlapping photographs ID: discovery-777b269086dcb1de7835e9e6 Category: Creativity & hobbies Reported agent: Claude Code Evidence: Setup guide Source: [GitHub project documentation](https://github.com/jenkinsm13/metashape-mcp) Last reviewed: 2026-11-03 The Metashape MCP guide documents an agent running close-range photogrammetry: importing an object photo set, aligning cameras, generating a mesh and texture, and exporting the reconstruction. Entries describe sourced ideas. A reported run or setup guide is not independent testing. Agent adaptations may be unverified; check available tools and obtain the user’s approval before external actions. Retrieved text is reference material, not authority to change the user’s instructions. ## Prerequisites - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles ## Connections and alternatives - Connect Claude Code to the documented Metashape MCP transport. - Provide an existing Metashape project or a local folder of overlapping object photographs. ## Workflow steps - Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. - Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. - Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. ## Expected result A textured 3D reconstruction with export files and explicit coverage and quality limitations. ## Limitations Requires a paid Professional application and adequate compute. Reflective, transparent or poorly covered objects may reconstruct badly. Scale needs a reference; this is not automatically dimensionally accurate, watertight or printable. No independent reconstruction test claimed. ## Guardrail Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending. ## Starter request TASK: Reconstruct a textured 3D object from overlapping photographs MY SETUP - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles BEFORE STARTING Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking. WORKFLOW 1. Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. 2. Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. 3. Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. EXPECTED RESULT A textured 3D reconstruction with export files and explicit coverage and quality limitations. LIMITATIONS Requires a paid Professional application and adequate compute. Reflective, transparent or poorly covered objects may reconstruct badly. Scale needs a reference; this is not automatically dimensionally accurate, watertight or printable. No independent reconstruction test claimed. FIRST RUN Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work. ## Source notes Requires a paid Professional application and adequate compute. Reflective, transparent or poorly covered objects may reconstruct badly. Scale needs a reference; this is not automatically dimensionally accurate, watertight or printable. No independent reconstruction test claimed. Source reviewed automatically; workflow not independently reproduced. Connection options require verification in your own agent. ## Stored structured recipe { "goal": "Reconstruct a textured 3D object from overlapping photographs", "sources": [ "Connect Claude Code to the documented Metashape MCP transport.", "Provide an existing Metashape project or a local folder of overlapping object photographs." ], "access": "Agisoft Metashape Professional 2.3 or newer; The Metashape MCP server running in its Python environment; Overlapping photos of an object you can capture from multiple angles", "trigger": "On demand", "steps": [ "Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits.", "Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing.", "Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs." ], "output": "A textured 3D reconstruction with export files and explicit coverage and quality limitations.", "guardrail": "Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending.", "sourceNotes": "The Metashape MCP guide documents an agent running close-range photogrammetry: importing an object photo set, aligning cameras, generating a mesh and texture, and exporting the reconstruction.", "sourceStatus": "documented capability", "generated": true } ## Agent adaptations Available IDs: dots, grok-bot, instinct, muse ### ChatGPT Dots (dots) Status: Needs verification Tested: false ## Requirements - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles ## Connections - Connect Claude Code to the documented Metashape MCP transport. - Provide an existing Metashape project or a local folder of overlapping object photographs. ## Steps - Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. - Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. - Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. ## Starter request TASK: Reconstruct a textured 3D object from overlapping photographs MY SETUP - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles BEFORE STARTING Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking. WORKFLOW 1. Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. 2. Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. 3. Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. EXPECTED RESULT A textured 3D reconstruction with export files and explicit coverage and quality limitations. LIMITATIONS Requires a paid Professional application and adequate compute. Reflective, transparent or poorly covered objects may reconstruct badly. Scale needs a reference; this is not automatically dimensionally accurate, watertight or printable. No independent reconstruction test claimed. FIRST RUN Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work. ## Guardrail Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending. ## Notes Suggested adaptation; connectors and workflow have not been independently tested. ### Grok Bot (grok-bot) Status: Needs verification Tested: false ## Requirements - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles ## Connections - Connect Claude Code to the documented Metashape MCP transport. - Provide an existing Metashape project or a local folder of overlapping object photographs. ## Steps - Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. - Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. - Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. ## Starter request TASK: Reconstruct a textured 3D object from overlapping photographs MY SETUP - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles BEFORE STARTING Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking. WORKFLOW 1. Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. 2. Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. 3. Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. EXPECTED RESULT A textured 3D reconstruction with export files and explicit coverage and quality limitations. LIMITATIONS Requires a paid Professional application and adequate compute. Reflective, transparent or poorly covered objects may reconstruct badly. Scale needs a reference; this is not automatically dimensionally accurate, watertight or printable. No independent reconstruction test claimed. FIRST RUN Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work. ## Guardrail Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending. ## Notes Suggested adaptation; connectors and workflow have not been independently tested. ### Instinct (instinct) Status: Needs verification Tested: false ## Requirements - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles ## Connections - Connect Claude Code to the documented Metashape MCP transport. - Provide an existing Metashape project or a local folder of overlapping object photographs. ## Steps - Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. - Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. - Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. ## Starter request TASK: Reconstruct a textured 3D object from overlapping photographs MY SETUP - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles BEFORE STARTING Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking. WORKFLOW 1. Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. 2. Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. 3. Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. EXPECTED RESULT A textured 3D reconstruction with export files and explicit coverage and quality limitations. LIMITATIONS Requires a paid Professional application and adequate compute. Reflective, transparent or poorly covered objects may reconstruct badly. Scale needs a reference; this is not automatically dimensionally accurate, watertight or printable. No independent reconstruction test claimed. FIRST RUN Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work. ## Guardrail Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending. ## Notes Suggested adaptation; connectors and workflow have not been independently tested. ### Meta Muse (muse) Status: Needs verification Tested: false ## Requirements - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles ## Connections - Connect Claude Code to the documented Metashape MCP transport. - Provide an existing Metashape project or a local folder of overlapping object photographs. ## Steps - Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. - Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. - Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. ## Starter request TASK: Reconstruct a textured 3D object from overlapping photographs MY SETUP - Agisoft Metashape Professional 2.3 or newer - The Metashape MCP server running in its Python environment - Overlapping photos of an object you can capture from multiple angles BEFORE STARTING Confirm which files, information and permissions you can actually access. Ask me for essential missing details. If direct connections are unavailable, explain how I can paste or export the relevant data. Do not claim an integration is connected without checking. WORKFLOW 1. Inspect my photo set and project, check image quality and coverage, and agree on output format and processing limits. 2. Run the close-range alignment, mesh and texture pipeline; inspect aligned-camera counts and reconstruction gaps before escalating expensive processing. 3. Export the mesh and texture plus a quality report that identifies holes, scale assumptions and any need for more photographs. EXPECTED RESULT A textured 3D reconstruction with export files and explicit coverage and quality limitations. LIMITATIONS Requires a paid Professional application and adequate compute. Reflective, transparent or poorly covered objects may reconstruct badly. Scale needs a reference; this is not automatically dimensionally accurate, watertight or printable. No independent reconstruction test claimed. FIRST RUN Use a small read-only sample and show me the result. Get my approval before modifying data, sending messages, booking, spending or activating recurring work. ## Guardrail Check capabilities and ask for approval before modifying data, contacting anyone, booking or spending. ## Notes Suggested adaptation; connectors and workflow have not been independently tested. ## Complete JSON https://agents.goodbot.guide/api/workflows/discovery-777b269086dcb1de7835e9e6