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→ Connectors → MCP — that page always reflects the production endpoint for your account, even if this doc is briefly out of date after a rebrand or region change.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

Paste this URL into the connector setup field:
https://api.pleyor.com/mcp
Your Pleyor 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 Pleyor

A Pleyor 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 Pleyor 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 Pleyor 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 pleyor-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, 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 Pleyor agents do I have?” → search + pleyor://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 pleyor://runs/{id} and explains the error

​
Next steps

Tool reference

The full surface — 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 needed.

Error codes

What each error means and how to recover.