Applies to:
- Plan - Any
- Deployment - Any
- Use case - Resolve dataset lookup errors despite browser access
Summary
MCPresolve_object can return Missing read access when a dataset URL or name lookup finds no accessible match. If you can open the dataset in the browser, retry with its UUID to bypass name lookup.
What is happening
Dataset browser URLs contain a URL slug. When you pass one to MCPresolve_object, it uses the slug as object_name and searches the dataset’s display name. If the slug differs from the name, the lookup can fail before any dataset rows are queried.
An empty lookup result can reflect a name mismatch or missing read permissions. The error alone does not distinguish these causes. UUID resolution bypasses name lookup but still checks read access.
Fix or suggestion
Option 1: Resolve by UUID (recommended)
-
List datasets with your personal API key, filtering by
org_nameandproject_name. Leavedataset_nameunset so a name mismatch does not hide the dataset. Replace the placeholders with your organization name, project name, and API key:Use your organization’s Braintrust API URL in place ofhttps://api.braintrust.devif you connect to another MCP endpoint, such as EU or BYOC. Find the dataset in the response’sobjectsarray and copy itsidandname. If needed, paginate withstarting_afterset to the last object’sidfrom the previous page. -
Call MCP
resolve_objectwith only the dataset type and UUID. Omiturl,object_name, and the other name fields: -
Use the returned
object_idfor subsequent dataset queries.
Option 2: Disambiguate name-based lookups
-
Set
object_nameto the exactnamereturned by the List datasets API, rather than itsurl_slug. -
Include both
org_nameandproject_nameto scope the lookup. Omiturlandobject_id:
How to confirm it worked
- The tool result’s text content contains JSON with the expected
object_id,object_name, andpermalink, without an error. Success does not require an explicitisError: falsefield. - Dataset row queries using that
object_idsucceed with the same credentials.