mcpwatch

← All servers

Grade B

Stunt Double

io.stuntdouble/mcp-server · v1.17.0 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do.

Source: https://github.com/stunt-double/stuntdouble-mcp

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 69 tool(s) to anyone, no credentials needed.
MediumMW1025 tool(s) can execute commands or delete data (remove_workspace_guideline, remove_actor_knowledge, delete_checklist, delete_workflow, remove_workflow_step). Require confirmation before the agent calls them.

What was checked

Public tools: get_me, list_workspaces, get_workspace, list_workspace_members, search, list_projects, get_project, create_project, list_project_mcp_servers, list_workspace_guidelines, add_workspace_guideline, update_workspace_guideline, remove_workspace_guideline, list_project_guidelines, add_project_guideline, set_project_guideline, list_actors, get_actor, create_actor, update_actor, list_actor_knowledge, add_actor_knowledge, remove_actor_knowledge, list_conversations, get_conversation, list_checklists, get_checklist, get_checklist_run, flag_check_verdict, run_checklist

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/io-stuntdouble-mcp-server-2766640b.svg)](https://www.mcpwatch.io/s/io-stuntdouble-mcp-server-2766640b)