Hugging Face MCP Server

Rate limit reached: log in or use your apiToken error

Pass HF_TOKEN in requests to authenticate. Get token from Hugging Face Settings > Access Tokens. Add Authorization: Bearer YOUR_TOKEN header to all API requests to avoid free tier limits.

Persistent rate limiting despite no recent usage

Rate limits are per 5-minute windows across all request types. Check your Billing page for current rate limit status across three buckets. Wait for 5-minute window reset or upgrade to PRO/Enterprise.

Inference API returns authentication errors

Serverless Inference API requires authentication. Add your HF token to requests. For heavy usage, switch to Inference Endpoints which provides dedicated resources and higher limits.

Cannot access models or datasets - permission error

Verify your account has access to requested model or dataset. For gated models, accept terms on model page. Check model visibility settings and ensure you're authenticated with correct token.