A
licenseA
qualityD
maintenanceSimulates real users navigating your app and delivers qualitative UX feedback, including persona-driven testing, auto-friction detection, and WCAG accessibility audits.
14
83 npm
2
MIT
Stunt Double
Server Details
Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do.
Ownership verified
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over 55 days
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- stunt-double/stuntdouble-mcp
- GitHub Stars
- 1
- Server Listing
- stuntdouble-mcp
TDQS
B3.1/5.0
Scored across 67 tools
Disambiguation4/5
Tools are mostly distinct resource/action pairs, and the lengthy descriptions clarify overlaps. Minor potential confusion remains among guideline/knowledge tools and `search` versus the many `list_*` getters, but no two tools appear to do the same thing.
Naming Consistency4/5
Nearly all names use snake_case with a verb-first pattern, making the set predictable. Deviations like `comment_on_pr` and the bare `search` are minor but keep this from being perfect.
Tool Count1/5
67 tools is far beyond the 3-15 sweet spot and past the 25+ threshold for being too many. Even across many subdomains, the surface is unwieldy and would be difficult for an agent to navigate efficiently.
Completeness3/5
Core testing entities like actors, checklists, interviews, and workflows have strong lifecycle coverage. However, projects lack update/delete operations, interviews lack delete, and some other entities have no create/delete paths, leaving notable gaps.
Publisher details
- Operator
- Stunt Double · Publisher source
- Operator website
- https://stuntdouble.io
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://www.stuntdouble.io/support/docs/api/mcp
- Trust center
- https://stuntdouble.io/security
- Restrictions
- https://www.stuntdouble.io/pricing
Related MCP Connectors
AI users run real tasks on your live site and show where they get stuck, with a replay of every step
AI-powered user research for everyone
A flock of AI users tests your deployed app and reports where real people get stuck, with fixes.
Run user research from any AI tool. Create studies, recruit participants, query insights.
Related MCP Servers
autousersofficial
AlicenseAqualityBmaintenanceEvaluate UX with AI personas and human raters directly from MCP-aware clients like Claude and ChatGPT.398 npmMIT- AlicenseNot gradedqualityAmaintenance▎ Enables AI assistants to unleash a crowd of role-played virtual users — impatient shoppers, seniors, keyboard-only users, privacy hawks, chaos monkeys — on a website. Each persona browses in a real Chromium browser, files UX/QA findings in character, and the site receives a damage report with an S–F survival grade. Accusations can be cross-examined by up to three independent verification engines1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to scan deployed web apps by sending a flock of AI users that identify UX issues, mobile breakage, and conversion path problems, returning prioritized, fix-ready findings.MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.