{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_f7yjk2m49t5z","handle":"orca-mcp-2","url":"https://wellknown.network/agents/orca-mcp-2","links":{"self":"https://wellknown.network/agents/orca-mcp-2/record.json","html":"https://wellknown.network/agents/orca-mcp-2","markdown":"https://wellknown.network/agents/orca-mcp-2/record.md","api":"https://wellknown.network/api/v1/agents/orca-mcp-2","status":"https://wellknown.network/api/v1/agents/orca-mcp-2/status","claim":"https://wellknown.network/agents/orca-mcp-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/orca-mcp-2/claim.json","badge":"https://wellknown.network/agents/orca-mcp-2/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/orca-mcp-2/history","tools":"https://wellknown.network/api/v1/agents/orca-mcp-2/tools"},"ard":{"identifier":"urn:air::server:orca-mcp-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"orca-mcp","summary":"MCP server that wraps the OrcaSlicer CLI: slice models, run parameter sweeps, and analyze G-code from any MCP client.","description":"# orca-mcp\n\n[![CI](https://github.com/jeff-roche/orca-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/jeff-roche/orca-mcp/actions/workflows/ci.yml)\n\nAn [MCP](https://modelcontextprotocol.io) server that wraps the **OrcaSlicer CLI**, letting any MCP compatible agent (Claude Code, Ollama, Codex, etc.) slice models, run parameter sweeps, and analyze the resulting G-code.\n\n```\nMCP client ──stdio──▶ orca-mcp ──subprocess──▶ orca-slicer CLI ──▶ G-code + estimates\n```\n\nWorks on **Linux, macOS, and Windows**, including Flatpak and AppImage installs of OrcaSlicer.\n\n## Why\n\nThe OrcaSlicer CLI can slice headlessly, but driving it by hand means juggling profile paths and grepping G-code comments. This server turns that into structured tools an AI agent can use: *\"slice this model with fan speeds of 20/40/60% and tell me which layers at the shoulder transition change\"* becomes a two-tool-call workflow.\n\n## Requirements\n\n- Python 3.10+\n- OrcaSlicer installed (native package, AppImage, Flatpak, or Windows/macOS installer)\n- Linux headless machines: `xvfb-run` recommended (`dnf install xorg-x11-server-Xvfb` / `apt install xvfb`) — some OrcaSlicer builds need a display context even in CLI mode. The server detects this and retries under xvfb automatically.\n\n## Install\n\n```bash\npip install orca-mcp\n\n# or from source:\ngit clone https://github.com/jeff-roche/orca-mcp\ncd orca-mcp && pip install .\n```\n\n## Configure your MCP client\n\n**Claude Desktop** (`claude_desktop_config.json`) or **Claude Code** (`claude mcp add`):\n\n```json\n{\n  \"mcpServers\": {\n    \"orca-mcp\": {\n      \"command\": \"orca-mcp\"\n    }\n  }\n}\n```\n\nIf OrcaSlicer isn't on your PATH, point the server at it:\n\n```json\n{\n  \"mcpServers\": {\n    \"orca-mcp\": {\n      \"command\": \"orca-mcp\",\n      \"env\": {\n        \"ORCASLICER_PATH\": \"/home/you/Applications/OrcaSlicer_Linux_V2.3.0.AppImage\"\n      }\n    }\n  }\n}\n```\n\n### How the slicer is located\n\nFirst match wins:\n\n1. `ORCASLICER_PATH` env var (any executable, including an AppIm…","publisher":null,"homepage":"https://github.com/jeff-roche/orca-mcp","repository":"https://github.com/jeff-roche/orca-mcp","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["3d-printing","gcode","mcp","orcaslicer","slicer"],"pricing":null,"endpoints":[{"url":"pypi:orca-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.688,"provenance":"derived"},{"slug":"media.3d","name":"3D & Design","confidence":0.563,"provenance":"derived"}],"categories":["dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"orca-mcp","registry":"pypi","observedAt":"2026-11-03T21:28:17.452Z","publishedAt":"2026-07-24T01:02:22.457000Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"orca-mcp","url":"https://pypi.org/project/orca-mcp/","firstSeenAt":"2026-09-10T09:24:55.497Z","fetchedAt":"2026-11-03T21:26:46.032Z","normalizedAt":"2026-11-03T21:26:46.032Z"}]},"firstSeenAt":"2026-09-10T09:24:55.497Z","updatedAt":"2026-11-03T21:28:17.452Z"}