Developers

Govern any AI agent in one API call.

Inspect, score, and police every tool call — outbound and inbound — with a single line of code. Typed SDKs, a machine-readable OpenAPI spec, and signed webhooks.

Get an API key API reference

No agent rewrite · decision in <100ms · redacted audit trail

agent.ts

import { AxioRank } from "@axiorank/sdk";
 
const axio = new AxioRank({ apiKey: process.env.AXIORANK_KEY! });
 
// One call governs a tool call. Throws if the gateway denies it.
await axio.enforce({
  tool: "aws.s3.deleteBucket",
  arguments: { bucket: "prod-backups" },
});

Quickstart

From zero to governed in three steps.

Install the SDK

TypeScript or Python — thin, typed wrappers over the gateway HTTP API.

npm i @axiorank/sdk

Create an API key

Mint a scoped key in the console under Settings → API keys.

axr_live_…

Guard your agent

Route tool calls through enforce() — one line, no agent rewrite.

await axio.enforce({ tool, arguments })

Build

One control plane, six surfaces.

Tool-call governance

Score, policy, and audit every outbound agent tool call in under 100ms.

Read the docs

MCP gateway

Govern any MCP server with no code changes via the stdio shim or HTTP proxy.

Read the docs

Inbound verification

Confirm the AI agents that visit your site with Web Bot Auth signatures.

Read the docs

Card preflight

Verify external MCP / A2A servers before your agent ever trusts them.

Read the docs

Webhooks & events

Subscribe to platform events with signed, retried, replayable delivery.

Read the docs

AI intelligence

Model-scored threat classes feed your policies as a first-class predicate.

Read the docs

SDKs & reference

Typed clients. A spec you can import.

Official SDKs wrap every endpoint with a typed surface and error taxonomy. Prefer your own tooling? The whole API is a machine-readable OpenAPI 3.1 document — drop it into Postman or any codegen.

Open API reference openapi.json

@axiorank/sdk

TypeScript · npm

npm i @axiorank/sdk

axiorank

Python · PyPI

pip install axiorank

@axiorank/mcp-gateway

MCP shim · npm

npx @axiorank/mcp-gateway

Model Context Protocol

Connect AxioRank to your AI.

AxioRank ships a remote MCP server — connect Cursor, Claude Desktop, or a ChatGPT connector and operate your control plane in natural language: score a tool call, verify a card, search the audit trail, manage agents & policies, and mint short-lived agent tokens. Authenticate with an API key, or use OAuth one-click connect.

Get an API key

Add to your MCP client

{
  "mcpServers": {
    "axiorank": {
      "url": "https://app.axiorank.com/api/mcp-server/mcp",
      "headers": { "Authorization": "Bearer axr_live_…" }
    }
  }
}

Prefer OAuth? Point a compatible client at the URL with no header — it discovers the authorization server and prompts you to sign in. Scope the key or token to least privilege (e.g. agents:read + logs:read for a read-only assistant).

Interoperate

Speaks 31 agent-interop protocols.

MCP, A2A, OAuth, x402, AP2, DID, ANS and more — verify identities and capabilities across the agent ecosystem. The coverage matrix is machine-readable.

View coverage protocols.json

Stay current

A stable contract, changes in the open.

Changelog

Every developer-facing change to the API, SDKs, and webhooks — newest first.

View changelog

Versioning & stability

What is stable, what counts as breaking, and our deprecation policy — 90-day notice, always announced here first.

Read the policy

Ship your first governed call today.

Create a key, drop in the SDK, and route a tool call through the gateway in minutes.

Get an API key Read the guide