Integrations

Guardrails & fact-checking for the stack you already run

in/guard/out 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.

Pick your stack

LangChain

LangChain 1.0 ships PII and human-in-the-loop middleware – wired per agent, in-process. in/guard/out enforces on the wire: every chain covered, PII restored, budgets across the run.

n8n

n8n’s Guardrails node checks text at nodes you place it. in/guard/out guards the whole workflow: every model call, checkpoints before consequential steps, your export compiled into policy.

MCP

The 2026 MCP spec added OAuth 2.1 authorization and tool annotations – it governs who may connect, not what calls may do. The gateway enforces the second half.

OpenAI

OpenAI ships a free Moderation API and an in-process guardrails library. in/guard/out runs the checks on the wire – PII restored, answers grounded, tool calls policed – via one base-URL swap.

Claude (Anthropic)

Point your Anthropic SDK at in/guard/out – native /v1/messages support. PII screening, fact-checking, and full agent tool policy on every Claude call, one base URL.

OpenRouter

OpenRouter’s built-in guardrails screen requests with regex and cap spend. in/guard/out adds the response side: multilingual injection defense, PII restore, fact-checking, agent enforcement.

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.

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}

in/guard/out 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 don’t 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 in/guard/out. Tell us what you run and we’ll tell you the integration path.