{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_2ysa2598veed","handle":"xfms-model-source","url":"https://wellknown.network/agents/xfms-model-source","links":{"self":"https://wellknown.network/agents/xfms-model-source/record.json","html":"https://wellknown.network/agents/xfms-model-source","markdown":"https://wellknown.network/agents/xfms-model-source/record.md","api":"https://wellknown.network/api/v1/agents/xfms-model-source","status":"https://wellknown.network/api/v1/agents/xfms-model-source/status","claim":"https://wellknown.network/agents/xfms-model-source/claim","claimApi":"https://wellknown.network/api/v1/claims","badge":"https://wellknown.network/agents/xfms-model-source/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air:xfms.vercel.app:server:xfms-model-source","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"XFMS — Model Source","summary":"Pick the right LLM for any task. Ranked shortlist with rationale across 8 evaluators.","description":"Pick the right LLM for any task. Ranked shortlist with rationale across 8 evaluators.","publisher":{"name":"dev.xpansion","url":null},"homepage":"https://xpansion.dev/xfms","repository":"https://github.com/VisionAIrySE/XFMS","version":"0.4.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://xfms.vercel.app/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-05-18T01:22:46.705077Z","publishedAt":"2026-05-18T01:22:46.705077Z","registryName":"dev.xpansion/xfms"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"productivity.hr","name":"HR & Recruiting","confidence":0.554,"provenance":"derived"},{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":0.54,"provenance":"derived"},{"slug":"commerce.ecommerce","name":"E-commerce Operations","confidence":0.51,"provenance":"derived"}],"categories":["ai","commerce","productivity"]},"observed":{"status":"live","statusReason":"Responded 2h ago.","lastOkAt":"2026-09-06T01:23:47.986Z","lastProbedAt":"2026-09-06T01:23:47.986Z","statusComputedAt":"2026-09-06T01:24:40.585Z","reliability30d":{"probes":1,"successRate":1,"p50Ms":302},"latestObservations":[{"at":"2026-09-06T01:23:47.986Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":302,"error":null,"detail":{"tools":[{"name":"rank","description":"Rank LLMs for a stated purpose. Returns a shortlist with weights, scores, and plain-English rationale per pick. Use when the user wants to see and compare alter"},{"name":"pick","description":"Return the single best LLM for a stated purpose. Concise output, no list. Use when the user has settled on the criteria and just wants one answer."},{"name":"discover","description":"Show which quality dimensions matter for a stated purpose, WITHOUT ranking any models. Returns the inferred weights and the discovery-walk trace. Useful for und"},{"name":"benchmark","description":"Run a live A/B test against the engine's TOP 3 PICKS for a stated purpose — the engine chooses the candidates from the full catalog. Generates 5 representative "},{"name":"compare","description":"Run a live A/B test between 2–5 user-specified models for a stated purpose. NO ranking step — the supplied model_ids ARE the candidate set. Generates 5 represen"}],"toolCount":5,"serverName":"xfms","capabilities":["experimental","tools"],"serverVersion":"1.27.2","protocolVersion":"2025-06-18"}}],"tools":[{"name":"rank","description":"Rank LLMs for a stated purpose. Returns a shortlist with weights, scores, and plain-English rationale per pick. Use when the user wants to see and compare alter"},{"name":"pick","description":"Return the single best LLM for a stated purpose. Concise output, no list. Use when the user has settled on the criteria and just wants one answer."},{"name":"discover","description":"Show which quality dimensions matter for a stated purpose, WITHOUT ranking any models. Returns the inferred weights and the discovery-walk trace. Useful for und"},{"name":"benchmark","description":"Run a live A/B test against the engine's TOP 3 PICKS for a stated purpose — the engine chooses the candidates from the full catalog. Generates 5 representative "},{"name":"compare","description":"Run a live A/B test between 2–5 user-specified models for a stated purpose. NO ranking step — the supplied model_ids ARE the candidate set. Generates 5 represen"}],"package":null},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"dev.xpansion/xfms","url":"https://registry.modelcontextprotocol.io/v0/servers/dev.xpansion%2Fxfms","firstSeenAt":"2026-09-05T23:20:59.369Z","fetchedAt":"2026-09-05T23:20:59.369Z","normalizedAt":"2026-09-05T23:20:59.369Z"}]},"firstSeenAt":"2026-09-05T23:20:59.369Z","updatedAt":"2026-09-06T01:24:49.171Z"}