All integrations

Run agents with Jam

Connect Jam once, and every run that names it works in Jam on the account you connected.

Connect JamOpens Settings → Connections in the console.

What an agent can do in Jam

Investigate bugs with Jam recordings: read console logs, network requests, user events and video transcripts.

Jobs on Rush that use Jam

How Jam connects

Jam is a remote MCP server, published by Jam, at https://mcp.jam.dev/mcp. Connecting it signs in through the MCP OAuth flow on Jam's side.

From Jam: Jam's MCP documentation · source code.

Connect it once in the console under Settings → Connections, or from your server with POST /me/connections. The sign-in finishes in a browser signed in to the console as the same person, and a link not finished within 10 minutes expires.

After that, a run that names jam in connections, or runs a saved agent that names it, gets it; your connections reach no run that does not name them.

POST https://api.phoenix.so/me/connections

{
  "type": "mcp",
  "name": "Jam",
  "url": "https://mcp.jam.dev/mcp"
}

Whose Jam account the agent uses

Your Jam connection is personal: it belongs to the person who signed in. A run started in the console uses that person's Jam, and a run started with an API key uses the Jam of the member who created the key.

To act for your own app's users, make each user an agent from your template and show them, signed in to your app, the sign-in link POST /o/{org}/agents/{agent}/connections returns. They sign in to their own Jam, and that agent's runs use their account and nothing else: never yours, never another user's.

More Developer Tools integrations

Frequently asked questions

How do I connect Jam to Rush?

Open Settings → Connections in the console and connect Jam, or send POST /me/connections with {"type":"mcp","name":"Jam","url":"https://mcp.jam.dev/mcp"} and open the authorize_url it returns while signed in to the console. The connection reads pending until the sign-in finishes, then connected.

Does every run get my Jam account?

No. A run gets your Jam connection only when it names it in connections ("connections": ["jam"]), or runs a saved agent that names it. A saved agent names its connections once, and every run of it gets them.

What can an agent do in Jam?

Investigate bugs with Jam recordings: read console logs, network requests, user events and video transcripts. 2 published jobs use it; this page lists them.

Can my app's users connect their own Jam?

Yes. Make each user an agent from your template, and they sign in to their own Jam through the link POST /o/{org}/agents/{agent}/connections returns. That agent's runs use their account alone.

Keep reading