Integration

LogRocket integration

LogRocket records user sessions in web and mobile apps. Get AI summaries (Galileo Highlights) of a user's recent sessions, optionally focused on a question, to add context to a support ticket or a sales follow-up; send a user's name, email and traits from your backend; and export the project's audit log (who viewed which session, settings changes). Summaries, user traits and audit entries are personal data. Highlights and user identification need a Pro or Enterprise plan. Each tool takes the org ID and project ID of the App ID (org/project, under Settings > Project Settings). Session recording, search and metrics are not offered by LogRocket's REST API. Authentication: an API key from Settings > API Keys, sent as Authorization: token <key>.

Connect LogRocket How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in LogRocket.Built from the 4 LogRocket tools below, on the connection you add once.

What you can do with LogRocket

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Highlight, 2 operations

get_highlightsGet highlightsGETReturns a Highlights request's status (PENDING, READY or FAILED) and, once READY, the AI summary across the user's sessions plus one per session, with replay links. Pass the id request_highlights returned.
request_highlightsRequest highlightsPOSTStarts an AI summary (Galileo Highlights) of a user's recent sessions and returns its id at once. Pass userEmail or userID. Read the result with get_highlights after 1 to 3 minutes, or pass webhookURL to receive it there. Pro and Enterprise plans.

Audit log, 1 operation

list_audit_logsList audit logsGETExports the project's audit log (Settings > Audit Log): who did what, including which session replays were viewed. Page with cursor: pass a millisecond timestamp first, then the cursor returned while has_next is true.

User, 1 operation

identify_userIdentify userPUTCreates or updates a LogRocket user's name, email and traits from your backend (overwrites the values sent). Traits not sent keep their value; a trait sent with a blank value is removed. Pro and Enterprise plans.

Use LogRocket from Claude Code, Cursor or Codex

Connect LogRocket in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its LogRocket operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect LogRocket

Create your workspace
Sign up free. Nothing to install.
Connect LogRocket once
Add your LogRocket connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.