Introduction
Payments on-call teams need a live incident room that keeps triage, commander decisions, and review metrics in one place. Build a live incident room with ToolJet MCP when you want a two-page app for card-processing incidents, and Jev, TypeSafe's decision model, returns severity, blast radius, customer impact, page-leadership probability, and likely cause for each open record while a person decides. In this build, an agent generated the app and the result is a structured ToolJet application, data, queries, and interface together, that the team keeps running. By the end, you can reproduce the war room, review page, and commander flow from the prompt in this article.
The War room: open incidents sorted by Jev's severity, the selected incident with its timer, metrics and Jev triage card, and the live timeline with the Slack preview.
The Review page: Jev versus commander agreement, MTTA to MTTR by severity, override rate by likely cause, and every incident from the last 7 days.
How Jev and the War Room Work
The War room page puts the open incident list on one side, the selected incident in the centre, and the live timeline plus staged Slack preview on the other side. You click a row, inspect the first three alerts, review the AI triage card, compare the suggested severity with the commander override, add a note, change status, and post updates without leaving the record. The layout keeps the command decision on the same screen as the timeline, so the commander sees current state and discussion history together. Jev returns severity, blast radius, customer impact, page-leadership probability, and likely cause, and the card shows confidence for each choice, the customer-impact score on a 1 to 5 scale, and the page-leadership probability as a percentage. The Review page summarizes agreement, overrides, MTTA, MTTR, and the last 7 days of incidents.
- Automatic triage for open incidents through the TypeSafe datasource
- Commander severity confirmation and override
- Live timeline updates and staged Slack posts
- Review metrics for agreement, MTTA, and MTTR
- Role-based write paths for commanders, engineers, and viewers
Set Up ToolJet MCP and the TypeSafe Datasource
ToolJet MCP connects your coding agent to your ToolJet workspace, so the agent can create the tables, queries and components for you. Set it up with the ToolJet MCP overview and the ToolJet MCP repository. Then add the TypeSafe datasource to the workspace and name it typesafe, which is the name the build prompt refers to.
- At build time: ToolJet MCP lets the agent create the app in your workspace.
- At run time: the app calls Jev, TypeSafe's decision model, through the typesafe datasource and shows its typed answers next to the record.
The Prompt That Recreates The Build
The real build took several passes, and the requirements are consolidated into one prompt that could have been used from the start. You can use the prompt in this article to reproduce the same two-page incident room in one shot.
Build a two-page Live Incident Room in ToolJet for the on-call and SRE team at a payments company that handles card processing for fintechs across the EU and UK. Use Jev through the TypeSafe datasource for every triage step. For each open incident, ask for severity, blast radius, customer impact, page-leadership probability, and likely cause, then cache the result on the incident and show the confidence, the customer-impact score, and the page-leadership probability in the UI. The War room page should show the open incident list, incident detail, the first three alerts, the triage card, commander severity controls, a note field, status controls, a live timeline, and a staged Slack preview. Confirming a decision writes the commander record and logs it to the timeline. Changing status updates the record and re-runs triage. The Review page should show agreement, overrides, incidents in 7 days, MTTA, MTTR, a dumbbell chart by severity, a bubble-lollipop chart by likely cause, and a searchable downloadable table of recent incidents.
How MCP Builds The Full App
ToolJet MCP works through the whole application, not the screen, so the incident data model, the pages, the component tree, the queries, and the wiring between them land as one structured ToolJet application. The generated app sits on a runtime that carries data connectivity, workflows, permissions, deployment, and ongoing change where supported, instead of leaving the team with a codebase to assemble and operate separately. The path stays open, so you can move from AI generation to visual editing and then to code where a case needs it.
Fixing The Customer Impact Scale
The customer-impact card showed the wrong scale, so the number looked lower than the triage meant. Jev returned the score as a 0-based legend index, not a 0 to 1 value, and the display now adds 1 before it is shown.
Tables Behind The Incident Room
The app ended up with three tables. ir_incidents stores the incident feed and cached AI triage, ir_decisions records commander severity decisions, and ir_timeline keeps the timestamped updates and staged Slack posts.
| Page | Components | What they cover |
|---|---|---|
| War room | 19 | Open incidents sorted by Jev's severity, the selected incident with Jev's triage card, and the live timeline. |
| Review | 8 | Jev versus commander agreement, MTTA to MTTR by severity, override rate by likely cause and a 7-day table. |
What Got Generated
| Metric | Result |
|---|---|
| Pages | 2 |
| ToolJet DB tables | 3 |
| Queries | 20 |
| Components | 27 |
| Code files to maintain | 0 |
| Repair cycles | 1 |
The components ToolJet MCP created, in the ToolJet inspector
Payments SRE and On Call Teams
Payments processors, fintech platforms, card issuers and acquirers, and any SaaS team running an on-call rotation can use this pattern. It fits wherever severity is argued about in a noisy chat channel and the team needs an AI first opinion, a clear commander decision and a record of how often the two agree.
Commander Engineer and Viewer Access
Three workspace groups control what each person can do. Incident Room - Commanders (and workspace admins) can confirm or override severity, change incident status and post the Slack update. These write queries are restricted to them on the server. Incident Room - Engineers can add timeline updates only. Support and leadership in Incident Room - Viewers can open both pages and read everything, but every action control is disabled for them. AI triage runs for every viewer so the board is always current.
SOC 2 Type II and GDPR Compliance in ToolJet
A Live Incident Room app usually has to pass a security review before rollout, and ToolJet supports that review with regular SOC 2 Type II audits, GDPR compliance and documented data protection controls. Reviewers can check the platform against standards they already use instead of starting from scratch.
For an incident room like this, security, legal, and auditors care about how incident notes and decisions map to review records. That is the path this section addresses for payments teams.
SOC 2 Type II and GDPR Compliance in ToolJet
Audited Standards: SOC 2 Type II and GDPR
- SOC 2 Type II audits: ToolJet undergoes regular SOC 2 Type II audits to validate its security, availability and confidentiality standards.
- GDPR compliance: ToolJet states that it fully complies with the General Data Protection Regulation and follows a GDPR-compliant data deletion policy, removing personal data on request or at the end of the retention period.
- Trust center: ToolJet points reviewers to trust.tooljet.com for the latest security documentation and compliance certifications.
Data Protection Controls Behind the Audits
- Encryption in transit and at rest: traffic between users and ToolJet servers uses TLS, and sensitive stored data is encrypted at rest.
- Encrypted workspace secrets: constants and secrets are encrypted before storage, and secrets resolve on the server so they never reach the browser.
- Audit logs for reviews: record user, app and data query activity with who, what, when and IP address.
- CJIS configuration guidance: criminal justice agencies get a guide to configuring a self-hosted deployment for CJIS Security Policy controls. There is no CJIS certification for platforms, so compliance remains the agency's responsibility.
For the Live Incident Room app, this gives security and legal reviewers audited evidence plus concrete controls to check, and teams with stricter data rules can pair it with self-hosted deployment to keep data on their own infrastructure.
Enterprise Features for Your Incident Room
An incident room handles severity decisions, timeline updates, and commander notes. ToolJet covers that governance at the platform layer, so you configure it once instead of rebuilding it in every app.
- SSO and SCIM: sign in with SAML, OIDC or LDAP, and provision users automatically
- Role-based access control: scope permissions to the app, the data source, and each query
- Audit logs: track every login, edit, and approval decision for compliance review
- Air-gapped deployment: self-host on Docker or Kubernetes so your data stays in your network
- Multiplayer editing: several builders work on the same app, with versioning and Git sync
- ToolJet AI inside your own deployment: run the AI features in your tenancy rather than a shared service
You could add a notification layer with ToolJet Workflows. For example, a workflow could fire when a commander posts an override, send a Slack message to the incident channel, email leadership through Gmail, and write the decision back to ir_decisions.
Final Takeaways
This build shows a two-page incident room that keeps the on-call flow in one place: open incidents, Jev triage, commander decisions, timeline updates, and a review page for agreement and recovery metrics. The team gets a shared view of each card-processing incident, plus a record of what the commander confirmed or overrode, so response stays tied to the same data that drives the list. If you are building a live incident room with ToolJet MCP, the useful part is not the screen alone, it is the editable ToolJet application behind it, ready for the next change.
Try ToolJet MCP
Build a live incident room with ToolJet MCP for your own alerts, then request a ToolJet demo for your incident data.
FAQs
What does ToolJet MCP do in this app?
ToolJet MCP turns the prompt into a working incident room inside ToolJet. It lands the data model, pages, queries, and interactions as one app that the on-call team can keep using and changing.
What does Jev return for each incident?
Severity, blast radius, customer impact, page-leadership probability, and likely cause. The triage card also shows confidence for each choice, and the customer-impact score is displayed on the scale used by the model.
Is Jev connected live and does it decide on its own?
No. Jev triages the current incident record through the TypeSafe datasource, and the incident commander still confirms or overrides the final severity. The model suggests, the person decides.
Can I use my own incident source with this pattern?
Yes. The build uses ToolJet DB as the incident feed stand-in, so you can map the same shape onto the source your team already uses. The prompt in this article is enough to reproduce the two-page app shape.
Do I need to write code for the incident room?
No. The generated app already includes the war room flow, the review page, and the commander actions, so you can stay in the visual builder unless a custom rule needs code. Jev and the database queries run the triage and decision flow.
What happens to the app after the agent finishes?
A structured ToolJet application keeps running inside the runtime. The runtime keeps the data connections, queries, permissions, and workflow paths together, so the team edits the same app as requirements change.
Can several people work on the same incident room at once?
Yes. The app is set up with commander, engineer, and viewer groups, so multiple people can work in the same incident room with different write access and the same shared record of updates.
Top comments (0)