The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Stunt Double listing page.
Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do.
Stunt Double deploys AI agents with realistic user personas to validate user journeys at scale. Create actors, run automated workflows and checklists against any web app, and surface friction points before real users encounter them. Integrates with Claude, Linear, GitHub, and Slack.
This repo holds plugin and MCP configuration (.cursor-plugin/plugin.json, root mcp.json, server.json), plus skills, agents, and Cursor rules. There is no package.json and no runnable server here — the MCP endpoint is hosted at https://app.stuntdouble.io/api/mcp from the main Stunt Double codebase. See CONTRIBUTING.md for how to validate edits and avoid confusing this folder with a Node package.
Go to Settings → Connectors → Add and paste:
Add the mcpServers block below to an MCP config file:
.cursor/mcp.json at the root of your project.~/.cursor/mcp.json on macOS/Linux (see Cursor MCP docs for your OS).Use only url for remote servers (Streamable HTTP is negotiated automatically). Extra keys such as "type": "streamable-http" are not part of Cursor's documented mcp.json shape and can break plugin validation.
Cursor marketplace (one-click install) expects a plugin layout: .cursor-plugin/plugin.json plus root mcp.json. Those files are in this repo. The plugin logo path is assets/logo.png (bundled in this repository). The server.json file is the separate MCP registry manifest for mcp-publisher and directory listings; Cursor's installer does not use it.
Authentication is handled automatically via OAuth 2.1 with PKCE. The first time your AI client connects, a browser window will open for you to sign in and authorise access to your Stunt Double account. No API keys or tokens required.
For Cursor, the OAuth redirect URI is fixed to cursor://anysphere.cursor-mcp/oauth/callback (docs).
| Tool | Description |
|---|---|
get_me | The account this connection acts as: id, email, name, timezone, notification channel |
Notification channel and timezone are account settings rather than workspace ones, so
they are the same answer in every workspace. Pass the timezone when creating a
scheduled workflow, or "every weekday at 9" becomes nine in UTC.
| Tool | Description |
|---|---|
list_workspaces | List your workspaces |
get_workspace | Get workspace details by ID or slug, including its admin-set controls (settings) |
list_workspace_members | List members of a workspace |
get_workspace reports the workspace security controls under settings: public
sharing, the feedback widget, self-hosted workers, and the network policy. They are
ceilings set by an admin, so a feature switched off there cannot be switched back on for
a single project.
| Tool | Description |
|---|---|
search | Search a workspace across projects, actors, checklists, interviews, automations, issues, goals, feedback, actor knowledge, insights, design reviews, project resources and conversations. Ranked, with optional filters |
search takes a workspace_id plus an optional query, types filter, project_id
filter and limit (max 50). Terms are matched as prefixes, so a partial word is enough.
Omit query to browse the most recently updated items. Results carry the id you need
for the matching getter, so it is usually cheaper than listing an entity type and
filtering the list yourself. Reach for it before creating anything, to find the actor or
checklist that already covers the job.
| Tool | Description |
|---|---|
list_projects | List projects in a workspace |
get_project | Get a project (the product tracked by checklists, workflows, feedback) |
create_project | Create a project (a product to track with checklists, workflows, feedback) |
list_project_mcp_servers | The MCP servers this project's runs can reach |
A project is archived, never deleted, and an archived project reads as missing from
every tool here. Registering an MCP server and attaching it to a project are
workspace-admin actions in the dashboard; list_project_mcp_servers is how you check
what tools a run will actually have before writing a checklist that depends on one.
Standing rules the team holds the product to: design system, tone of voice, brand, content, accessibility, compliance, security, performance, or shared knowledge. A guideline is owned by the workspace and attached to the projects it applies to, so one rule can hold for every project without being retyped. Whatever is in force is rendered into every checklist run, design review, interview and triage for that project.
| Tool | Description |
|---|---|
list_workspace_guidelines | The workspace library, with how many projects hold each rule |
add_workspace_guideline | Add a rule to the library, optionally attaching it to projects |
update_workspace_guideline | Edit a rule, switch it off, or apply it to every design review in the workspace |
remove_workspace_guideline | Remove a rule from the library, detaching it from every project |
list_project_guidelines | The rules this project is held to |
add_project_guideline | Record a rule and hold this project to it |
set_project_guideline | Attach a library rule to a project, detach it, or switch it off there |
Two switches decide whether a rule is in force for a project: the library's enabled
and the attachment's. list_project_guidelines folds them into one enabled so you
never have to reason about both. A rule with apply_to_design_reviews set also holds for
design reviews raised from Slack or Linear, which carry no project to attach it through.
Codify a standard as a guideline rather than repeating it in each checklist, and search the library before writing a new rule: attaching the one that already exists keeps the team's standard in a single place to edit.
| Tool | Description |
|---|---|
list_actors | List active actors in a workspace |
get_actor | Get actor details including system prompt and capabilities |
create_actor | Create a new actor in a workspace |
update_actor | Update actor name, description, system prompt, capabilities, or status. Set status to "archived" to soft-delete |
| Tool | Description |
|---|---|
list_actor_knowledge | List knowledge entries for an actor |
add_actor_knowledge | Add a knowledge entry to an actor |
remove_actor_knowledge | Remove a knowledge entry |
| Tool | Description |
|---|---|
list_conversations | List conversations, optionally filtered by actor |
get_conversation | Get a conversation with its messages |
| Tool | Description |
|---|---|
list_checklists | List checklists in a workspace |
get_checklist | Get checklist details, checks, and recent runs |
get_checklist_run | Get a checklist run with per-check results |
run_checklist | Trigger a checklist run (async). Returns run ID |
create_checklist | Create a browser-based QA checklist (host via project or URL, actor, instructions, checks) |
update_checklist | Update a checklist (pass checks to replace the full set) |
delete_checklist | Delete a checklist and its checks and runs |
| Tool | Description |
|---|---|
list_workflows | List workflows in a workspace |
get_workflow | Get workflow details with steps and recent runs |
run_workflow | Trigger a workflow run (async). Returns run ID |
get_workflow_run | Get a workflow run with step-level details |
create_workflow | Create a workflow (multi-step automation) |
update_workflow | Update a workflow's name, description, or trigger |
toggle_workflow | Activate or pause a workflow |
delete_workflow | Delete a workflow and its steps and runs |
add_workflow_step | Append a step to a workflow |
update_workflow_step | Update a workflow step type, config, or sort order |
remove_workflow_step | Remove a step from a workflow |
| Tool | Description |
|---|---|
list_feedback | List feedback for a project, newest first |
get_feedback | Get a feedback submission with its replies |
update_feedback_status | Update feedback status |
| Tool | Description |
|---|---|
list_pull_requests | List pull requests for a GitHub repository |
get_pull_request | Get details for a GitHub pull request (title, author, branches, stats) |
comment_on_pr | Post a comment on a GitHub pull request |
Structured user interviews — actors or generated personas run through a discussion guide (sections + questions/tasks) against a target URL, then Stunt Double synthesises themes and recommendations.
| Tool | Description |
|---|---|
list_interviews | List interviews in a workspace, optionally filtered by project |
get_interview | Get an interview with its discussion guide (sections + items) and participants |
create_interview | Create a new interview in a project (name, target URL, research brief) |
update_interview | Update an interview's name, target URL, research brief, or status |
add_interview_section | Add a section to the discussion guide |
add_interview_item | Add a question or task to a section |
add_interview_participant | Attach a participant — either an existing actor or an ad-hoc persona_spec |
get_interview_participant | Get a participant including their full transcript from the run |
get_interview_report | Get the current synthesised report (summary, themes, recommendations, per-question rollup) |
launch_interview | Launch the interview round (async). Returns the trigger run ID |
regenerate_interview_report | Re-run synthesis on existing transcripts (async). Returns the trigger run ID |
Most MCP clients (Claude, Claude Code, Cursor) surface these as slash commands. Each is a self-contained recipe: which tools to call, in what order, and how to report back.
| Prompt | Description |
|---|---|
validate_design | Validate a live design, prototype, or preview URL (Figma Make, Claude artifact, v0, staging) with AI personas |
verify_change | Verify a shipped or previewed code change by running an actor through the affected flows, optionally commenting on the PR |
run_user_research | Run a structured multi-persona interview study and synthesise themes and recommendations |
triage_feedback | Triage user feedback on a project: cluster it, reproduce issues with an actor, and update statuses |
setup_guardrails | Stand up checklists for critical flows plus a workflow that re-runs them on a schedule or on deploy/PR events |
check_brand | Audit a product against brand and tone-of-voice guidelines, flagging deviations with evidence |
check_design_system | Audit a live product against its design system (typography, colour, spacing, components) on rendered pages |
check_compliance | Check a product against legal and compliance requirements and collect evidence for counsel to review |
check_continuity | Check continuity across surfaces (pricing, terminology, promises) between marketing, product, docs, and emails |
stuntdouble_guide | Orientation for Stunt Double: what it does, when to reach for it, and the full tool catalogue |
Workspace member administration (inviting/removing members) is available in the web dashboard.
This server uses Streamable HTTP transport. The endpoint is:
From the repo root:
More context in CONTRIBUTING.md. GitHub Actions runs the same checks on push and pull requests.
MIT