{"id":"jojojotarou-askuserquestionplus","name":"AskUserQuestionPlus","homepage":null,"repo_url":"https://github.com/JoJoJotarou/AskUserQuestionPlus","category":"devtools","subcategories":[],"tags":["mcp","model-context-protocol","ai-ml","devtools","forms","websocket","express","ui","interactive"],"what_it_does":"AskUserQuestionPlus is an MCP server (Streamable HTTP) that opens a web-based questionnaire UI and returns user-selected answers back to an LLM/tool call via the MCP tool `ask_user_question_plus`.","use_cases":["Collect structured user input from an LLM conversation (e.g., preferences, triage questions, onboarding surveys).","Use with Claude Code, Codex, and Gemini CLI workflows via MCP over HTTP.","Interactive multi-question forms with single/multiple choice and an optional free-text “Other” input."],"not_for":["Production scenarios that require strict authentication/authorization controls for interactive user data without additional hardening.","Use cases needing programmatic REST endpoints (non-MCP) for fully automated, headless submission.","Environments where automatic browser interaction is disallowed or undesirable."],"best_when":"You want lightweight, local or internal-tool style interactive questionnaires driven by an LLM, and you can run the server behind trusted network boundaries.","avoid_when":"You need robust security controls (authz, audit logging, CSRF protection guarantees) or multi-tenant exposure without deploying additional safeguards.","alternatives":["Other MCP questionnaire/form tools","Building a custom MCP server that renders server-side forms and uses signed callbacks","Direct form UI + separate backend endpoint (non-MCP) integrated by the agent through an API/tool layer"],"af_score":50.2,"security_score":27.0,"reliability_score":31.2,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:28:01.183428+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":"http://localhost:3456/mcp","has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["None documented (public server assumed in README)"],"oauth":false,"scopes":false,"notes":"The README does not describe authentication, authorization, or signed sessions for the MCP server; it only documents startup parameters and tool schemas."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information provided (appears to be an open-source npm package)."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":50.2,"security_score":27.0,"reliability_score":31.2,"mcp_server_quality":72.0,"documentation_accuracy":80.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":20.0,"rate_limit_clarity":20.0,"tls_enforcement":35.0,"auth_strength":15.0,"scope_granularity":10.0,"dependency_hygiene":55.0,"secret_handling":30.0,"security_notes":"No authentication/authorization is described. TLS requirement and CSRF/session security are not documented. The service uses dependencies like `express`, `ws`, `open`, `zod`, and `@modelcontextprotocol/sdk`; dependency hygiene is unknown from the provided content. Treat it as potentially exposing interactive user data unless deployed with network restrictions and additional safeguards.","uptime_documented":0.0,"version_stability":50.0,"breaking_changes_history":40.0,"error_recovery":35.0,"idempotency_support":"false","idempotency_notes":"Not documented; interactive questionnaire submissions are likely non-idempotent per session.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Authentication/security expectations are not documented; agents should assume the server is trusted unless you add protections.","Automatic browser tab opening/closure is described; headless or locked-down environments may not work as expected.","Timeout behavior exists (default 10 minutes) but retry semantics and partial completion handling are not documented.","The tool schema is provided, but exact MCP method names, transport details, and error codes are not shown in the README excerpts, so agent-side handling may require experimentation."]}}