AI assistants (MCP)

Pellio has an MCP server, so AI assistants such as Claude, ChatGPT and Cursor can work with your video library: find videos, read analytics, see who watched, list leads, and update or import videos. It’s on every plan. See pellio.io/mcp for what people ask it.

Connect an assistant

The server URL is https://api.pellio.io/mcp.

• Claude: Settings → Connectors → Add custom connector, then paste the URL.
• ChatGPT: add a custom connector (MCP) in its settings and paste the URL.
• Cursor: add { "mcpServers": { "pellio": { "url": "https://api.pellio.io/mcp" } } } to your mcp.json.
• Claude Code: run claude mcp add --transport http pellio https://api.pellio.io/mcp, then /mcp to sign in.

The assistant opens Pellio: sign in if you aren’t already, check what it’s asking for, and click Allow.

What it can do

It acts as you, with your role and folder access, in your workspace (it can switch to your other workspaces). It can list and search videos and folders, read a video’s details, analytics and viewers, list leads, check storage and bandwidth, get embed codes, update a video’s title, description, privacy, tags or folder, import a video from a link, and create share links. It can’t change billing, API keys or your team, and plan limits apply as usual (for example, leads need the Standard plan).

Changes it makes appear in the audit log as yours, marked “via an AI assistant”.

Disconnect

In Settings → Security → Connected apps, click Disconnect next to the app. It loses access straight away.

For your own agents and scripts

Instead of signing in, send a Pellio API key as Authorization: Bearer pk_…. A read-only key gives a read-only connection. See API keys and the REST API.