Connect Portkey MCP for AI Agents

Portkey acts as a central hub, pulling cost data from every vendor you connect. You can ask your agent for total spending across all models and providers in one query, giving you complete financial visibility.

Yes. The MCP lets you set hard budget policies per team or project. If the usage hits the limit, the system automatically restricts access to prevent further overspending.

You don't have to guess. You can ask your agent to retrieve the detailed logs for that specific call ID. It will show you the exact error code, the root cause, and which gateway component failed.

You can trigger an export of all your AI logs into a single JSON file. This creates a comprehensive, time-stamped record ready to be submitted as part of any formal compliance review.

Yes, because it unifies everything. Instead of managing five separate dashboards, you manage one central gateway view that aggregates costs, logs, and configurations from all providers.

Portkey supports 1,600+ LLMs including OpenAI, Anthropic, Google, Mistral, Azure OpenAI, AWS Bedrock, Cohere, Hugging Face, and many more. Use the list_models tool to see the full catalog available via your gateway.

Portkey provides granular visibility into token usage, latency, and costs per model, team, or virtual key. You can create budget policies with hard limits to prevent runaway spending. The gateway also supports caching to reduce duplicate calls and fallbacks to cheaper models when appropriate.

Yes! Portkey allows you to submit Like/Dislike feedback for any logged LLM call. This data helps improve model selection, evaluate agent performance, and build RLHF datasets for fine-tuning.