{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_32evm6xpxmrj","handle":"radia-mcp","url":"https://wellknown.network/agents/radia-mcp","links":{"self":"https://wellknown.network/agents/radia-mcp/record.json","html":"https://wellknown.network/agents/radia-mcp","markdown":"https://wellknown.network/agents/radia-mcp/record.md","api":"https://wellknown.network/api/v1/agents/radia-mcp","status":"https://wellknown.network/api/v1/agents/radia-mcp/status","claim":"https://wellknown.network/agents/radia-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/radia-mcp/claim.json","badge":"https://wellknown.network/agents/radia-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:radia-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"radia-mcp","summary":"MCP servers for the Radia CAE ecosystem -- Cubit / build123d / gmsh / NGSolve / PEEC / IH + 30+ specialized knowledge subpackages (panel-review, CLN MOR, COMSOL multilingual RAG, electromagnet, magnetic-materials, motor, accelerator, NMR/MRI, NDT, metamaterial, WPT, TEAM benchmark, etc.).  See READ…","description":"# radia-mcp\n\nFor fewer client processes, use the [capability packs](docs/design/capability_packs.md).\nThey combine related domains with startup-selected profiles while preserving old\ncommands. `paper-writing` now includes grant and poster tools as well as slides\nand figures; genre-specific scoring remains separate.\n\nFor standard client settings, safe editable updates and behavioral acceptance,\nsee the [maintenance procedure](docs/maintenance.md) and\n[known-issue ledger](docs/maintenance-known-issues.md).\n\n[![PyPI](https://img.shields.io/pypi/v/radia-mcp.svg)](https://pypi.org/project/radia-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/radia-mcp.svg)](https://pypi.org/project/radia-mcp/)\n[![License: BSD-3-Clause](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](LICENSE)\n\n> **First-and-only public Model Context Protocol (MCP) server suite for\n> Coreform Cubit, Gmsh, build123d, and the Radia CAE ecosystem —\n> including differential geometry and Mathematica integration.**\n> Pioneering MCP territory for mesh generators worldwide.\n\n**Killer demo (30 seconds)**: ask Claude to derive the Kelvin transform\nfactor by hand — it gets stuck on a 3×3 Jacobian + 27-term Laplacian.\nThen ask it to use `differential-forms` + `mathematica` together:\n\n```\n> verify_with_mathematica(identity=\"kelvin\")\n```\n\nClaude pulls the recipe, sends it to Wolfram, reports back\n\n```\nk=1:  Laplacian(psi) = 0          [harmonic — factor R/|y| is correct]\nk=2:  Laplacian(psi) ≠ 0          [factor wrong]\nk=3:  Laplacian(psi) ≠ 0          [factor wrong]\n```\n\n— in 8 seconds.  The `kelvin_factor = R/|y|` that takes half a day\nin vector calculus appears as the conformal weight λ^((n−2k)/2) of a\nk-form, and Mathematica verifies it symbolically.\n\nAuthored by the **Sugawara Lab (菅原研究室)**, Kindai University —\nwhere the lab-standard primary pair is **build123d (CAD authoring) +\nCubit (hex meshing)**, with Gmsh as the post-processing workhorse.\n\n---\n\n## Why this exists\n\n`radia-mcp` lets an …","publisher":{"name":"Kengo Sugahara","url":null},"homepage":null,"repository":"https://github.com/ksugahar/Radia","version":"1.4.53","license":"BSD-3-Clause","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:radia-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","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":0.825,"provenance":"derived"},{"slug":"media.3d","name":"3D & Design","confidence":0.745,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":0.745,"provenance":"derived"}],"categories":["ai","data","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":"radia-mcp","registry":"pypi","observedAt":"2026-09-10T11:28:07.289Z","publishedAt":"2026-09-07T10:53:57.232458Z","latestVersion":"1.4.53"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"radia-mcp","url":"https://pypi.org/project/radia-mcp/","firstSeenAt":"2026-09-10T11:25:52.972Z","fetchedAt":"2026-09-10T11:25:52.972Z","normalizedAt":"2026-09-10T11:25:52.972Z"}]},"firstSeenAt":"2026-09-10T11:25:52.972Z","updatedAt":"2026-09-10T11:28:07.289Z"}