Tools & capabilities

You don’t call these tools yourself — your AI assistant picks the right ones based on what you ask. This page is a reference for what’s possible and what permissions each capability needs.

Permission scopes

The consent screen shows exactly which scopes will be granted when you connect. Every client covered in the setup guide receives all three scopes, including connectors with no configurable scope field. If you’re building your own client, you can request a read-only connection by sending an explicit scope with just the read scopes.

Scope	Grants
`studies:read`	Read your studies, questions, groups, logic, and settings
`interviews:read`	Read interviews and results in your studies
`studies:write`	Create and edit studies, questions, groups, and logic (includes `studies:read`)

Scopes are fixed when a client connects. To change them (for example, to add write access to a connection that was approved read-only), disconnect the client and connect it again so the consent screen runs with the new scopes. Scopes are an upper bound, not a bypass: every request is also checked against your organization role and each study’s access policy, so an agent can never see or change more than you can in the dashboard.

Tools

Studies

Tool	Description	Scope
`list_studies`	List your studies newest-first, with status filters, search, and optional activity counts	`studies:read`
`get_study`	Full study detail: settings, quota, branding, messages, languages, and share links	`studies:read`
`create_study`	Create a new study (requires an owner, admin, or creator organization role)	`studies:write`
`edit_study_settings`	Edit title, description, status, mode, quota (a total cap, or per-link-parameter buckets with a matching-value policy), pause URL, access policy, branding, study context, or languages	`studies:write`
`edit_interview_message`	Edit the welcome, thank-you, or screen-out message	`studies:write`
`archive_study`	Archive a study — the only removal MCP offers; reversible in the dashboard	`studies:write`

Questions

Tool	Description	Scope
`list_questions`	List questions in display order with type, group, notes, and logic flags	`studies:read`
`get_question_details`	One question’s full configuration, media download links, logic rules, and quotas	`studies:read`
`add_questions`	Add questions at a position or append them to a group	`studies:write`
`edit_question`	Edit any question field, including its type	`studies:write`
`set_question_quotas`	Cap completes per option on a multiple choice question (`equals` or `includes` match, 0 closes an option); pass the full list, an empty list clears it	`studies:write`
`remove_questions`	Remove questions (soft delete); reports logic rules left dangling	`studies:write`
`reorder_questions`	Reorder all questions in an ungrouped study	`studies:write`

Question groups

Tool	Description	Scope
`list_question_groups`	Group hierarchy, order, and randomization settings	`studies:read`
`add_question_group`	Create a top-level group or a subgroup (groups nest at most two levels)	`studies:write`
`edit_question_group`	Rename a group or toggle child randomization	`studies:write`
`move_questions_to_group`	Move questions into a group or back to the top level	`studies:write`
`remove_question_group`	Ungroup or delete a group (delete cascades to its questions)	`studies:write`

Randomizers

Randomizers are weighted split tests: each participant is routed to exactly one arm, and an arm shows one question or one question group (or is left empty as a placeholder while you build). Use a randomized question group when you only want to shuffle order.

Tool	Description	Scope
`list_randomizers`	Randomizers with their arms, weights, and each arm’s target question or group	`studies:read`
`add_randomizer`	Create a split test over existing questions or groups (2–12 arms, weights total 10,000 basis points)	`studies:write`
`edit_randomizer`	Rename a randomizer or replace its arms, weights, and targets	`studies:write`
`remove_randomizer`	Dissolve a randomizer keeping all its content (`ungroup`), or delete it with everything in its arms (`delete`)	`studies:write`

Logic rules

Tool	Description	Scope
`get_logic_rules`	Logic rules for one question or the whole study	`studies:read`
`add_logic_rule`	Add a conditional rule: skip to a question, move to a group, end the interview, screen the participant out, or redirect	`studies:write`
`edit_logic_rule`	Edit an existing rule	`studies:write`
`delete_logic_rule`	Delete a rule	`studies:write`

Interviews & results

Tool	Description	Scope
`list_interviews`	List interviews with status filters; simulated interviews excluded by default	`interviews:read`
`get_interview`	One interview with its question-and-answer conversation	`interviews:read`
`get_study_stats`	Completion funnel, drop-off by question, weekly trends, or per-question answer aggregates	`interviews:read`
`export_study_data`	Interview responses as CSV — one row per interview, one column per question	`interviews:read`

Capabilities

Tool	Description	Scope
`get_capabilities`	The ground truth on what Versive supports: question types with defaults, logic and group rules, and unsupported features with workarounds	`studies:read`

Help center

Tool	Description	Scope
`search_docs`	Search this help center for product and how-to documentation — credits and billing, sharing, recruiting, roles, MCP setup, API and SDK basics	`studies:read`
`read_doc`	Read one help-center page, or a single section of it, as Markdown	`studies:read`

Prompts

Prompts are ready-made analysis workflows. Most clients surface them in a prompt or command menu (in Claude, look under the connector’s entry in the tools menu).

Prompt	What it does
`study-summary`	Structured research summary: themes with supporting quotes, contradictions, confidence, and follow-up questions
`study-insights`	Per-question thematic insights, mirroring the dashboard’s Insights tab
`study-insights-summary`	Executive summary for stakeholders: overview, takeaways, participants, recommendations
`custom-insight`	Runs your own analysis question across all transcripts in a study
`interview-summary`	One interview: overview, participant profile, sentiment, takeaways, and quality/fraud ratings

Resources

Resource	Description
`versive://study/{study_id}`	A study as a JSON document; clients that support resource browsing can list your accessible studies

Good to know

Your agent handles fetching and pagination on its own — there’s nothing to configure. A few things to know:

Question media links expire. get_question_details returns each asset’s stable url plus a usable download_url. Private download links last one hour, with their UTC expiry in download_url_expires_at. Fetch details again to refresh a link. A null download URL means the private file is currently unavailable.
Numbers can differ from a casual dashboard glance. Mock and archived interviews are never exposed over MCP, and simulated interviews are always reported separately from real ones — so MCP counts reflect real research activity only.
A few things still happen in the dashboard. Figma prototype tasks, tree tests, and conjoint questions are configured there (their text stays editable via MCP), and stimulus media is attached there. Agents check the get_capabilities tool for the full list of unsupported features, each with a workaround, so they’ll route around these on their own.

​Permission scopes

​Tools

​Studies

​Questions

​Question groups

​Randomizers

​Logic rules

​Interviews & results

​Capabilities

​Help center

​Prompts

​Resources

​Good to know