Unwrap

Run a custom instruction or question across all entries in a Sample Reference and return prevalence statistics plus example results. Requires sample_reference_id each call — use the id from sample_feedback_entries or classify_feedback_entries output (stateless server does not retain prior samples).

Classify entries in a Sample Reference into predefined labels and create a sub-sample per label. Pass sample_reference_id from sample_feedback_entries or a prior classify call; MCP output lists sample_reference_id per label for follow-up tools.

List all available filters for a view. Returns every filter name that can be used for filtering. Use this at the start of the conversation to discover the available filters.

Call this when the user wants root cause analysis, next steps, what is driving a feedback group, issue resolution, support insights, solution insights, or bot capability gaps on an Unwrap taxonomy group. Returns a step-by-step workflow playbook to run with other Unwrap tools (sample_feedback_entries → analyze_entry_text → classify_feedback_entries). Does NOT return the insights themselves.

Call after list_views to load the full Unwrap usage guide and color palette for the selected view. Recommended at the start of every MCP session, but the server is stateless and other tools work without it.

Leave feedback for the Unwrap team about your experience using this MCP — when a tool produced a confusing result, a workflow felt awkward, or you'd recommend a change. If you don't have confident answers for every field, ask the user yourself before calling this tool. Do not include user PII.

List the views connected feedback integrations and source coverage.

List exact allowed values for a segment. Use this before filtering when you need the precise value spelling.

Get the authenticated org's view's. Returns view_id, view_name, and org_name for org's view's.

Plot charts and tables over time or by breakdown. Use this when the user is asking about an issue or group over time, when they want top groups or top issues shown visually, or when a visual comparison would make the answer clearer. Prefer filter + breakdown_field over many hand-authored series: scope with series filters (e.g. Group is Huddle), then set breakdown_field to split that population (Group, leaf_group, source, or a segment name like Sentiment). Use breakdown_field=none (All Feedback) for a single volume line under the filters. Choose the chart type based on whether the user wants a time trend, an aggregate ranking, or a share comparison. After calling it, still return written analysis alongside the chart. Use search_segments or list_field_values before filtering or selecting numeric segments.