Integrations

Guardrails & fact-checking for the stack you already run

The proxy meets your architecture where it is: an OpenAI-compatible surface for anything with an SDK, a checkpoint API for orchestrators, and an MCP gateway for tool servers. No rewrite is the design goal, not a marketing line.

§01 Pick your stack

LangChain

Add guardrails to LangChain and LangGraph agents without middleware sprawl: a base-URL swap for model calls, a callback for tool checkpoints, one audit trail.

n8n

Guard n8n AI workflows without rebuilding them: point AI nodes at the proxy, gate consequential nodes with a checkpoint, and compile your workflow into policy.

MCP

Route MCP clients through a gateway that inspects tools/call before forwarding, scans results for injection, and pins server manifests against rug pulls.

OpenAI

Put guardrails in front of the OpenAI API without changing your code: PII screening, hallucination checks, tool-call policy – via a base-URL swap in any SDK.

Claude (Anthropic)

Run Claude Opus, Sonnet, and Haiku behind a guardrails pipeline: PII screening, hallucination checks, and content safety – without changing your client code.

OpenRouter

One guardrails pipeline across every OpenRouter model – Gemini, Claude, GPT, Llama, DeepSeek, Qwen, Mistral – with per-model cost and quality evidence.

LM Studio & local models

Local models still hallucinate and still obey injections. Run the same guardrail pipeline in front of LM Studio and any OpenAI-compatible local server.

§02 The three surfaces behind every integration

① The LLM boundary

POST /v1/chat/completions

The core vantage point – it sees everything the model sees: the full context, the declared tools, the chosen actions, and the sources those actions should be grounded in. Point any OpenAI SDK at it.

② MCP gateway

POST /mcp/{server}

The proxy speaks MCP between the agent and its servers. It inspects tools/call before forwarding – a deny is an error the client can’t ignore – scans the returned result, and pins the tool manifest.

③ Checkpoint API

POST /v1/checkpoint

A Policy Decision Point for steps that never touch an LLM. Ask "may I proceed?" and get allow / deny / require-approval. Drop-in clients: an n8n node, a LangChain callback, a Python SDK.

Don’t see your stack? It probably still works.

Anything that speaks the OpenAI API or can POST JSON can use the proxy. Tell us what you run and we’ll tell you the integration path.