AI integrations in Python

Expose Python services as tools for AI agents and call Claude, OpenAI, Gemini or self-hosted models from your own code.

Get started

Expose a service as an MCP tool and call it from an AI agent, end to end.

Expose your systems to agents

Tool exposure Turn each assigned service into one MCP tool with a schema derived from its input and output. Prompts Serve a gateway's skills to agents as MCP prompts. Sharing with clients Give the teams that configure AI agents a gateway's details as one document.

Call models from your code

LLM invoke Call a model from a Python service and get token usage with each response. Chat Hold multi-turn conversations with managed history. Skills Reuse instructions as LLM system context and as MCP prompts.

Protect data and access

Security Require authentication on every gateway with API keys, Basic Auth or bearer tokens. PII removal Replace personally identifiable information before a response reaches a model. Rate limits Cap each agent's traffic through its security definition.

Shape and audit traffic

Response shaping Strip noise, neutralize hostile content and cap sizes in tokens. Argument validation Refuse invalid tool calls before any service code runs. Audit log Record the caller, tool, outcome and sizes of each agent request.

Operate the AI layer

GitOps Keep the whole AI configuration as enmasse YAML in version control. Export Export each gateway as a registry-format server.json.

More resources

Observability Watch MCP and LLM audit events with alert rules and LLM-driven diagnosis. Cost and limits Cap cost and traffic with token limits, timeouts and size caps.