Session Replay

Bug reports with the full context already attached — console errors, network requests, interactions, and the screen recording — read straight from your agent…

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • List Domains: Every domain this account has claimed, with the team it belongs to and whether it has been verified. A domain that cannot be read yet is listed and says why.
  • List Reports: Bug reports filed against a domain this account has claimed and verified, newest first. One page at a time: the answer says how many matched in total, how many it carries, and the offset
  • Get Report: One report in full: what page it was filed on, how long the capture ran, where it stands, and the console, network and interaction logs, with repeated console errors collapsed into one ent

What data it sees

Do you need an account

No: the server works without sign-in

Bug reports with the full context already attached — console errors, network requests, interactions, and the screen recording — read straight from your agent, without opening the dashboard.

Point it at a domain you've claimed in Session Replay and it can search the reports filed against it, read one in full, pull a still from the recording at the exact moment something failed, and move the report through triage.

Tools

  • list_domains — the domains this account can read, and why any of them can't yet
  • list_reports — search a domain's reports by text, status, or date range, newest first
  • get_report — one report in full, with repeated console errors collapsed and counted
  • get_frame — a still from the recording at a given offset; the offsets worth asking for are already in the report, on every console error, failed request, and interaction
  • set_status — move a report through triage. The person who filed it is told, so resolved tells them their bug is fixed

Before you connect

You'll need a Session Replay account with the domain claimed and verified, and a Professional plan — the server refuses tools on lower tiers and names the plan in the refusal. Sign-in is OAuth; nothing to paste, no API key.

How to connect

How to connect Session Replay to Claude

The server address to paste into Claude settings:

https://session-replay--info-0q2s.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Session Replay to ChatGPT

The server address to paste into ChatGPT settings:

https://session-replay--info-0q2s.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Session Replay to Cursor

The server address to paste into Cursor settings:

https://session-replay--info-0q2s.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (5)

Raw names from tools/list. Only developers need these.

list_domainsEvery domain this account has claimed, with the team it belongs to and whether it has been verified. A domain that cannot be read yet is listed and says why.
list_reportsBug reports filed against a domain this account has claimed and verified, newest first. One page at a time: the answer says how many matched in total, how many it carries, and the offset that reaches the next page. Each row is a summary - enough to choose one; get_report has the rest of it.
get_reportOne report in full: what page it was filed on, how long the capture ran, where it stands, and the console, network and interaction logs, with repeated console errors collapsed into one entry carrying a count.
get_frameA single frame from the screen recording at a moment you name. The offsets worth asking for are in the report already: console errors, failed requests and interactions all carry one.
set_statusSet where a report stands. The person who filed it sees every status change, so resolved tells them their bug is fixed. Answers with the token, where the report now stands and when it was resolved - not the report itself, which get_report has.