Data Sources Beginner

Rootly MCP Integration

3 min read Updated June 05, 2026
Incidents, severity, response timelines, on-call schedules, and retrospectives from Rootly, read-only through the planner during AI analyses.

Rootly runs incident response: declaring incidents, tracking severity and timelines, paging the right people, and capturing what happened afterward. Connecting Rootly to clariBI puts reliability operations next to the customer and revenue impact those incidents cause.

Why connect Rootly

Incident data sits in the response tool, separate from the support load and revenue effects an outage produces.

With Rootly connected, you can ask "How many Sev1 incidents did we have this quarter and what was the mean time to resolve?", "Which services cause the most incidents?", or "How long did the checkout outage last and who responded?" and the AI engine reads the answer live.

How the connection works

clariBI talks to Rootly through its hosted MCP server at https://mcp.rootly.com/sse. Authentication uses an OAuth flow that clariBI registers itself for (no developer console setup on your side). Tokens stay encrypted server-side and never leave clariBI in clear form.

sequenceDiagram
    actor U as You
    participant C as clariBI
    participant V as Rootly
    U->>C: Click Authorize with Rootly
    C->>V: Open OAuth authorization
    V-->>U: Grant read access?
    U->>V: Approve
    V-->>C: Authorization code
    C->>V: Exchange code for tokens
    V-->>C: Access + refresh tokens
    C->>C: Encrypt and store credentials
    C-->>U: Connection ready

Available tools

clariBI exposes the read-only Rootly tools that the vendor's MCP server publishes at connection time. Write operations (create, update, delete, send, refund) are filtered out by a name-pattern blocklist before any tool reaches the analysis engine, so connecting Rootly cannot modify data on the vendor side.

The exact tool inventory depends on the Rootly features your account has access to. After connecting, try a few natural-language questions to see what Rootly data clariBI can pull.

Data flow during analysis

When you ask a question that maps to Rootly, the AI engine routes to the right tool, reads the result, and pairs the answer with a chart you can pin to a dashboard.

sequenceDiagram
    actor U as You
    participant C as clariBI
    participant AI as AI engine
    participant V as Rootly
    U->>C: Ask a question about incident response data
    C->>AI: Plan the analysis
    AI->>V: Call the right tool
    V-->>AI: Tool result
    AI->>AI: Summarize and chart
    C-->>U: Answer plus visual

Setting up the connection

  1. Open Data Sources in the clariBI sidebar.
  2. Click Add data source.
  3. Open the MCP Servers tab.
  4. Click the Rootly card.
  5. Click Authorize with Rootly.
  6. Sign in to Rootly in the popup window and grant the requested read scopes.
  7. Back in clariBI, give your data source a name.
  8. Click Finish.

Permissions and data access

clariBI connects through Rootly's OAuth flow and inherits the connected user's access. The catalog exposes read tools only (reading incidents, severities, timelines, and schedules); clariBI never declares, edits, or resolves an incident. Disconnect anytime from Settings → Integrations in clariBI.

Troubleshooting

ErrorCauseFix
"No incidents returned"The connected user is scoped to a team or environment without incidents in the window.Widen the time range or confirm the user can see the relevant team in Rootly.
"Resolve times look wrong"An incident is still open, or it was resolved without a resolution timestamp.Filter to resolved incidents, or check that responders close incidents with a timestamp in Rootly.

Related articles

Related Articles

Data Sources Beginner

Foqal MCP Integration

Tickets, request topics, resolution timelines, and CSAT, NPS, and CES scores from Foqal's Slack and…

5 min read
Data Sources Intermediate

Apideck MCP Integration

Normalized records across Accounting, CRM, HRIS, ATS, File Storage, E-commerce, and Issue Tracking …

5 min read
Data Sources Beginner

Hugging Face MCP Integration

Public Hugging Face Hub data: model, dataset, and Space search, research-paper search, repository d…

5 min read

Still Need Help?

Can't find what you're looking for? Our support team is here to help you succeed with clariBI.