Troubleshooting
Authentication fails or loops
Authentication fails or loops
- Confirm you are signed in to Listen Labs in the browser that opens for consent
- Remove and re-add the MCP server in your client to trigger a fresh OAuth flow
- Check that your client supports remote OAuth MCP (not only local stdio servers)
"Access denied" on a study
"Access denied" on a study
Your Listen Labs user does not have access to that study’s organization. Verify access in the dashboard.
Analysis tool returns nothing useful
Analysis tool returns nothing useful
get_study_analysis requires a completed analysis run. Check list_studies for has_analysis: true. New or in-progress studies may not have analysis yet.Client shows "Method not allowed"
Client shows "Method not allowed"
The server is stateless and only accepts
POST on /mcp. Ensure your client uses Streamable HTTP, not SSE session polling on GET /mcp."Study is currently being updated"
"Study is currently being updated"
Another edit or save is in progress. Wait a moment and try again.
"No permission to launch"
"No permission to launch"
Your role may allow editing but not starting recruitment. Ask an admin for launch permissions.
Changes aren't visible to respondents
Changes aren't visible to respondents
Edits on live studies stay in draft until published. Ask your assistant to publish or launch the study.
"Multiple folders match"
"Multiple folders match"
That folder name is used in more than one place. The error lists the full path of each match, so repeat your request with the full path, such as
Research / Q3 2026."No folder named ..."
"No folder named ..."
Filing a study requires a folder that already exists. The error lists the folders that do exist. Pick one of those, or ask your assistant to create the folder first.
A folder won't delete
A folder won't delete
Only empty folders can be deleted. Move the studies and subfolders out first, then delete.
Folder counts don't match a filtered list
Folder counts don't match a filtered list
Folder study counts describe the whole folder. They ignore keyword and status filters, so they will not match a filtered list of studies. This is expected.