Bring Llm
to CrewAI

Log in to the Anthropic Console, go to Account Settings > API Keys and click Create Key. Copy the key immediately — it starts with sk-ant- and won't be shown again. You can also create workspace-scoped keys to control spending by use case.

Use the list_models tool to see all available Claude models. Current models include Claude Sonnet 4, Claude Opus 4 and Claude Haiku variants, each with different capabilities, context windows and pricing. The model ID format is like claude-sonnet-4-20250514.

Yes! Pass a messages array with alternating 'user' and 'assistant' roles. Each message has a 'role' and 'content' field. Claude will continue the conversation based on the full message history. Example: [{"role":"user","content":"Hello"},{"role":"assistant","content":"Hi!"},{"role":"user","content":"What's 2+2?"}].

Use create_batch_message with an array of independent message requests. Each request is processed asynchronously and costs 50% less than individual requests. Use get_batch_message to check progress and results. Batches are ideal when you have many unrelated prompts to process.

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.