Peractor in your chat apps
Drive Peractor from Claude, ChatGPT, Codex, or Claude Code — with scopes you grant and can revoke.
People who work with coding agents already live in a chat window. Peractor plugs into all of them: say "run the Linear task about the login bug through the review workflow" in your own chat, and it happens.
Peractor is a remote MCP server, the open protocol those apps speak, so anything that speaks MCP can connect. Claude, ChatGPT, Codex, and Claude Code are simply the ones people use.
Connect one
In Claude Code, one command registers Peractor (self-hosting? use your own address):
claude mcp add --transport http peractor https://peractor.com/mcpIn Claude, ChatGPT, or Codex, add a connector or MCP server pointing at the same address. The first use opens your browser: sign in to Peractor, pick the organization the chat should act on, and approve. If you belong to several organizations, connect once per organization.
Read the domain on the consent screen. A
connecting app reports its own name and logo, and those can be faked. The
domain is the one thing it cannot fake. Approve
claude.ai or chatgpt.com, not a
look-alike.
What you are granting
| Scope | Lets the chat |
|---|---|
| Read | List and read projects, workflows, personas, tasks, and runs. |
| Act | Create and edit tasks, start runs, approve or send back a gate, review and restart runs, answer mid-run questions, cancel runs, fire triggers. |
| Author | Propose configuration changes — workflows, personas, connector settings. |
| Admin | Manage the organization — members and invites, projects, runner machines, apps. Off unless you tick it, and most connections never need it. |
Read is always included. The other three are checkboxes you tick or leave. Everything the chat does, it does as you — the same memberships and permissions you have in the app, and no more. A read-only install cannot start anything, whatever a task description tells the model to do.
Configuration changes are shown before they land
Starting a run appears in the chat as a tool call you confirm, and you can cancel the run if you change your mind. Configuration is stricter: an Author-scoped change is staged into a plan, the chat shows you the actual file diff rather than a summary of it, and only "yes, apply it" applies exactly the plan you read. If anything changed after you looked, the apply refuses and you review again.
Manage and revoke
Settings → Connected apps lists every chat you have connected — which app, which scopes, when it was last used. Disconnect cuts it off immediately, and the next use starts a fresh consent. Connections refresh themselves while in use and expire on their own after 90 days unused.
Chat apps and API keys are different things. A connected chat acts as a person, with that person's permissions, granted per organization through a browser consent. An API key is a service credential for systems — CI, Zapier, your own backend — created by an admin and tied to nobody's sign-in. Automations get keys; humans in chats get this.