Skip to content
Agentic Control Plane

Install ACP into the coding agent you already run

One command finds the agents on your machine and adds a hook to each. Pick yours below for what the hook sees and what it cannot stop.

$curl -fsSL https://agenticcontrolplane.com/install.sh | bash

Building the agent yourself (CrewAI, LangGraph, Anthropic Agent SDK, OpenAI Agents SDK)? See Frameworks for guided starter code.

Clients

The AI tools your team already uses.

Step-by-step install guides for each AI client, with the caveats vendor docs leave out. There are two install paths: a local hook for coding agents, or an MCP server connection for chat clients. What each client lets ACP see and enforce differs, and /coverage lists it.

Using a client we don't list? If it speaks MCP (Windsurf, Continue, ChatGPT’s connectors) or the OpenAI chat-completions API, point it at ACP. Calls that go through the ACP MCP endpoint or proxy are checked and logged. The client's own built-in tools are not.

Want cost too? Hooks cover tool calls. To meter model spend, cache-hit rate, and the loop-vs-leaf cost X-ray, route your model calls through the proxy with one base-URL change.

Identity Providers

Your identity provider. Your users.

The installed hooks authenticate with a workspace key. A caller can send a JWT from your IdP instead. ACP checks the signature against your JWKS endpoint, then issuer, audience and expiry, before it trusts any claim. That identity is valid only in your workspace. Your users stay in your directory.

Auth0 OIDC + JWKS
Okta OIDC + JWKS
Microsoft Entra ID OIDC + JWKS
Google Identity Google Workspace SSO
Firebase Auth Firebase tokens
Any OIDC provider Configurable issuer, audience, JWKS URI

How agent identity works →

What every integration gets

Whichever client you install, the calls ACP sees go through one policy pipeline and land in one log. Per-client limits are on /coverage.

Identity binding
Each call carries your workspace key, tied to one person, or a verified JWT. ACP checks it before deciding the call.
Policy enforcement
Audit-only by default; ask and deny rules apply once you turn them on
PII detection
Scan and redact sensitive data
Audit logging
Identity-attributed trail on every action
Budget controls
Per-user and per-agent spend limits
Workspace isolation
A key or token is checked against one workspace and only works there; its audit rows are stored under that workspace

Keep your clients. Add the checks.

Free to start. Add checks to the AI client you already use in a few minutes.

$curl -fsSL https://agenticcontrolplane.com/install.sh | bash

Already installed? Open your console · For IT teams