Hugging Face
Connect to Hugging Face Hub APIs: search spaces/papers, explore models and datasets.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Hugging Face, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
Hugging Face's MCP server programmatically connects to Hub APIs: semantic search for spaces and papers, exploration of datasets and models, and access to compatible MCP Gradio tool spaces. Backed by an HF token; running third-party Gradio tool spaces means executing external code paths worth scrutinizing.
Key features
- Search spaces, models, papers
- Dataset exploration
- Gradio tool-space access
Use cases
- Discover models and datasets
- Invoke community Gradio tools