{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_s2xeut543h5b","handle":"hf-model-explorer-mcp","url":"https://wellknown.network/agents/hf-model-explorer-mcp","links":{"self":"https://wellknown.network/agents/hf-model-explorer-mcp/record.json","html":"https://wellknown.network/agents/hf-model-explorer-mcp","markdown":"https://wellknown.network/agents/hf-model-explorer-mcp/record.md","api":"https://wellknown.network/api/v1/agents/hf-model-explorer-mcp","status":"https://wellknown.network/api/v1/agents/hf-model-explorer-mcp/status","claim":"https://wellknown.network/agents/hf-model-explorer-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/hf-model-explorer-mcp/claim.json","badge":"https://wellknown.network/agents/hf-model-explorer-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/hf-model-explorer-mcp/history","tools":"https://wellknown.network/api/v1/agents/hf-model-explorer-mcp/tools"},"ard":{"identifier":"urn:air::server:hf-model-explorer-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"hf-model-explorer-mcp","summary":"MCP server for searching, comparing, and hardware-sizing Hugging Face models","description":"# hf-model-explorer-mcp\n\nAn [MCP](https://modelcontextprotocol.io) server that lets AI agents search, compare, and\nright-size Hugging Face models — including estimating whether a model will actually fit\nin your available GPU VRAM before you download 15GB of weights and find out the hard way.\n\nWorks with any MCP-compatible client: Claude, Google Antigravity, Cursor, and others.\n\n## Why\n\nPicking a model off Hugging Face usually means checking the model card, guessing at\nparameter count, mentally doing GB-per-precision math, and hoping it fits your GPU.\nThis wraps that into tools an agent can call directly, so you can ask things like:\n\n> \"Find me a small instruction-tuned model I can run locally on a 12GB GPU\"\n\nand get an actual, sized answer instead of a guess.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `search_models` | Search HF Hub by query and task, sorted by downloads/likes/recency |\n| `get_model_details` | Full details on one model: params, license, tags, task |\n| `compare_models` | Side-by-side comparison of 2–4 models |\n| `check_hardware_fit` | Estimates VRAM needed at fp32/fp16/int8/int4 and whether it fits your GPU |\n| `find_similar_models` | Finds lighter/heavier/similar-sized alternatives for the same task |\n\n## Install\n\n```bash\npip install hf-model-explorer-mcp\n```\n\nOr run directly without installing, via `uvx`:\n\n```bash\nuvx hf-model-explorer-mcp\n```\n\n## Configure\n\n### Claude Desktop / Claude Code\n\nAdd to your MCP config (`claude_desktop_config.json` or `.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"hf-model-explorer\": {\n      \"command\": \"uvx\",\n      \"args\": [\"hf-model-explorer-mcp\"]\n    }\n  }\n}\n```\n\n### Google Antigravity\n\nAdd to `~/.gemini/antigravity/mcp_config.json` (path may vary by Antigravity version —\ncheck Settings → MCP Servers in the IDE):\n\n```json\n{\n  \"mcpServers\": {\n    \"hf-model-explorer\": {\n      \"command\": \"uvx\",\n      \"args\": [\"hf-model-explorer-mcp\"]\n    }\n  }\n}\n```\n\n## Example\n\n```\nUser: I want to run an instruction-tuned 7B-ish m…","publisher":null,"homepage":"https://github.com/Greekkgod/MCP-Inspector","repository":"https://github.com/Greekkgod/MCP-Inspector","version":"0.1.1","license":"MIT","protocols":["mcp"],"tags":["ai","huggingface","llm","mcp","ml","model-context-protocol"],"pricing":null,"endpoints":[{"url":"pypi:hf-model-explorer-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":"ai.model-access","name":"Model Access","confidence":1,"provenance":"declared"}],"categories":["ai"],"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":"hf-model-explorer-mcp","registry":"pypi","observedAt":"2026-10-24T17:29:03.903Z","publishedAt":"2026-09-24T07:15:10.685429Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"hf-model-explorer-mcp","url":"https://pypi.org/project/hf-model-explorer-mcp/","firstSeenAt":"2026-09-24T10:27:38.361Z","fetchedAt":"2026-10-24T17:27:34.735Z","normalizedAt":"2026-10-24T17:27:34.735Z"}]},"firstSeenAt":"2026-09-24T10:27:38.361Z","updatedAt":"2026-10-24T17:29:03.903Z"}