Postman is where teams build, test, and document their APIs. Requests live in collections, collections live in workspaces, and monitors run those collections on a schedule. Connecting Postman to clariBI turns that API workspace into something you can count and chart: how many collections exist, who owns them, and whether the monitors are passing.
Why connect Postman
API assets pile up across workspaces, and no one has a single view of how many collections exist, which are documented, or which monitors keep failing.
With Postman connected, you can ask "How many collections does each workspace hold and when were they last updated?", "Which monitors failed runs this week?", or "How many API specs do we have versus documented collections?" and the AI engine reads it live.
How the connection works
clariBI talks to Postman through its hosted MCP server at https://mcp.postman.com/mcp. 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 Postman
U->>C: Click Authorize with Postman
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 Postman 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 Postman cannot modify data on the vendor side.
The exact tool inventory depends on the Postman features your account has access to. After connecting, try a few natural-language questions to see what Postman data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Postman, 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 Postman
U->>C: Ask a question about API workspace and monitoring 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
- Open Data Sources in the clariBI sidebar.
- Click Add data source.
- Open the MCP Servers tab.
- Click the Postman card.
- Click Authorize with Postman.
- Sign in to Postman in the popup window and grant the requested read scopes.
- Back in clariBI, give your data source a name.
- Click Finish.
Permissions and data access
clariBI connects through Postman's OAuth flow and inherits the connected user's team and workspace access. The catalog exposes read tools only (reading workspaces, collections, environments, API specs, and monitor results); clariBI never creates, edits, or runs a collection. Disconnect anytime from Settings → Integrations in clariBI.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "No collections returned" | The connected user belongs to a different Postman team, or the workspace is private to another member. | Confirm the team and workspace in Postman and that your user has been added to them, then reconnect. |
| "Monitor results look empty" | The monitor has not run inside the analysis window, or it is paused. | Widen the time range, or check that the monitor is active and on a schedule in Postman. |