Skip to main content
The connector takes two minutes to add. Once it’s in, your chat client can drive Orisu end-to-end.
Current public endpoint. The Orisu MCP server lives at https://api.orisu.ai/mcp. The same URL is shown in your Orisu dashboard under Settings → Connectors → MCP — that page always reflects the production endpoint for your account, even if this doc is briefly out of date after a rebrand or region change.

​
In Claude

1

Open Connectors

Claude → Settings → Connectors → Add custom connector.
2

Paste the Orisu MCP endpoint

Paste this URL into the connector setup field:
Your Orisu dashboard’s Settings → Connectors → MCP page always shows the live endpoint for your account. Copy from there if this URL ever lags a deploy or you’re on a non-production environment.
Click Continue.
3

Sign in to Orisu

A Orisu login window opens (OAuth). Sign in with the account you normally use. The first time, you’ll see a consent screen listing the scopes the connector needs. Approve to continue.
4

Pick a workspace

If your Orisu account belongs to multiple workspaces, you’ll be asked which one to bind the connector to. All subsequent tool calls run against that workspace.
5

Try it

Open a new chat and ask: “List my recent Orisu runs.” Claude calls list_runs, the connector returns your latest runs, and Claude summarises them. That’s the loop working.
The first message in a fresh chat triggers the model to load the orisu-workflows skill, the canonical playbook that teaches it the patterns. After that, follow-up turns are fast because the playbook is already in context.

​
In ChatGPT

ChatGPT’s connector setup follows the same shape. Paste the same MCP endpoint URL, complete the OAuth flow, and you’re in. Refer to ChatGPT’s connector documentation for the latest UI flow.

​
What to ask first

Good first prompts that exercise the full surface:
  • Discovery: “What Orisu agents do I have?” → search + orisu://agents
  • Building: “Create a workflow that takes a photo and produces a 3-second video clip with motion.” → create_agent + validate_graph + canvas render
  • Running: “Trigger my last agent with this prompt and wait for it to finish.” → trigger_run + wait_for_run + asset URLs
  • Iterating: “That run failed — what happened?” → reads orisu://runs/{id} and explains the error

​
Next steps

Tool reference

What each of the 20+ tools does.

In-chat canvas

Understand the live canvas, when it appears, what’s interactive.

API keys

For scripts and server-to-server, no OAuth required.

Error codes

What each error means and how to recover.