Bring Model Discovery
to CrewAI

Log in to Hugging Face, go to Settings > Access Tokens, click New token, give it a name and select scopes (read is sufficient for browsing, write if you need to create repos). Copy the token immediately — it starts with hf_.

Yes! Use list_models with a search query. While the search endpoint doesn't directly filter by pipeline_tag, you can search by task name (e.g. search='text-generation') and then use get_model or get_model_tags to verify the pipeline_tag of specific models.

Yes! Use list_model_files with the model ID (e.g. 'google-bert/bert-base-uncased') to see the complete file tree including model weights (.safetensors, .bin), config files, tokenizer files and README. Optionally set a path to browse a specific subdirectory like 'onnx' or 'pytorch'.

Yes! Use create_discussion with the repo type ('model', 'dataset' or 'space'), the repo ID and a title. This creates a new discussion thread on the repository. You can use list_model_discussions first to check existing threads before creating a new one.

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.