MCP server official
Risk level
low
20/100

Hugging Face MCP Server ↗

Hugging Face MCP Server is an officially published MCP server from Hugging Face. Anomity scores its risk at 20 out of 100 (low).

network:outbound credentials:access

Analysis summary

Hugging Face MCP Server is an officially published MCP server from Hugging Face. Anomity scores its risk at 20 out of 100 (low).

Hugging Face's official server exposes models, datasets, Spaces, and inference to agents, so an assistant can search the hub, read model cards, and call hosted inference endpoints as tools.

Capabilities are outbound network access and credential access for the hub token. The supply-chain angle is the one to think about: an agent that can discover and invoke arbitrary community models and Spaces is an agent whose behaviour depends on artifacts nobody on your team reviewed. Model cards and dataset descriptions are also free text reaching the model's context. Prefer allow-listing the models an assistant may call over granting open hub access.

Why this entry scored 20 out of 100

This profile starts at the catalog's neutral base of 50. Because the entry is officially published, trust adjusts the score by -40. Declared high-risk capabilities add +10 (capped at +30). It matches no dangerous capability combinations. The clamped result is 20, placing it in the low band.

See the full scoring formula →

Findings

  • Published by the vendor Trust offset
    Contribution to score: -40
  • 1 high-risk capability: credentials:access High
    Contribution to score: +10

Capabilities

Every capability the entry declares, with the security implication of each.

  • network:outbound Outbound network
    Can make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access.
  • credentials:access Credentials access
    Reads provider API keys, OAuth tokens, or other secrets from the host keychain or environment.