A simple MCP server to operate on the Postman API
Scoring was not performed
Output schemas are not documented. Tools return CallToolResult with text content, but the structure and fields of the returned JSON/data are never specified. Agents cannot plan downstream tool calls or extract specific fields without trial-and-error.
Parameter descriptions lack minimum length and detail for key fields. addWorkspaceToPrivateNetwork's 'parentFolderId' description is only 16 characters ('The `0` value.'), below the 20-char minimum for substantive descriptions. createCollectionFolder's 'folder' parameter lacks clarity on optionality and format.
Error handling and recovery guidance are absent. Tools have no mechanism to communicate retryability, user-fixable errors, or next steps. An agent that receives an error has no guidance on what to do.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 42 | 2026-07-28+ | v2 |
| 2026-03-09 | F | 44 | - | v1 |
Tool annotations (readOnlyHint, destructiveHint, idempotentHint) are present only on getEnabledTools. All WRITE tools (addWorkspaceToPrivateNetwork, createCollectionComment, createCollectionFolder, createCollectionFork) lack annotations to flag destructive behavior and idempotency status.
Complex parameter schemas (e.g., createCollectionComment's 'tags' object with nested properties) lack usage examples or validation constraints. The description says 'Information about users tagged in the `body` comment' but does not clarify required vs optional nested fields or how to structure the object.