{"id":"jianger666-cursor-feedback-extension","name":"cursor-feedback-extension","homepage":null,"repo_url":"https://github.com/jianger666/cursor-feedback-extension","category":"ai-ml","subcategories":[],"tags":["mcp","cursor-extension","human-in-the-loop","interactive-feedback","sidebar-ui","webview","javascript","open-vsx","open-source","ai-assistant"],"what_it_does":"Cursor Feedback is a Cursor IDE extension plus an MCP server that provides an interactive human-in-the-loop feedback step. The Cursor AI agent calls an MCP tool (interactive_feedback), the extension shows a sidebar UI to collect user feedback (text/images/files), and the MCP server returns the feedback to the agent so it can continue within the same conversation.","use_cases":["Gather user approval or edits after the AI produces a work summary","Create a repeatable review loop inside Cursor for iterative tasks","Collect feedback that includes screenshots/images and referenced project file paths","Avoid re-consuming Cursor monthly request quota by keeping interaction in one conversation"],"not_for":["Production systems requiring strict guarantees about data handling or compliance","Use cases that need a public REST/GraphQL API for server-to-server automation","Scenarios where the user cannot safely provide local file paths/images to an AI workflow","Environments that require high assurance of dependency/vulnerability management"],"best_when":"You want a lightweight, IDE-native approval/review loop for Cursor-generated outputs, including rich feedback (images/files) from the local workspace.","avoid_when":"You need formal enterprise-grade security/compliance evidence, or you cannot tolerate that local project context (paths and potentially selected files/images) may be sent through the agent workflow.","alternatives":["mcp-feedback-enhanced (Python-based MCP feedback loop mentioned by the project)","Build a custom MCP server + Cursor extension using @modelcontextprotocol/sdk","Use Cursor built-in review/feedback mechanisms (if available) without an external MCP feedback loop"],"af_score":57.0,"security_score":36.5,"reliability_score":30.0,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:37:32.080760+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["No explicit auth described for MCP tool calls; configured via local Cursor MCP config"],"oauth":false,"scopes":false,"notes":"The README describes local MCP server configuration (npx/cursor-feedback@latest) and a tool interface (interactive_feedback) without any mention of authentication, API keys, or scope controls."},"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 for the extension/MCP server is provided. The README references Cursor request quotas, but that is not a pricing model of this package."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":57.0,"security_score":36.5,"reliability_score":30.0,"mcp_server_quality":65.0,"documentation_accuracy":60.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":10.0,"tls_enforcement":60.0,"auth_strength":15.0,"scope_granularity":10.0,"dependency_hygiene":45.0,"secret_handling":60.0,"security_notes":"No authentication/authorization model is described for the MCP tool/extension interactions. The workflow involves local project context (paths, images/files) and thus creates a risk of inadvertent data exposure to the AI workflow. README does not document data handling details, transport security for any HTTP API used by the extension, or whether secrets/tokens are ever logged.","uptime_documented":0.0,"version_stability":35.0,"breaking_changes_history":30.0,"error_recovery":55.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":true,"known_agent_gotchas":["Tool is interactive; the agent must wait for user feedback via the sidebar before continuing.","On timeout (default 300s), the extension/agent workflow supports auto-retry; ensure agent logic avoids duplicating work if feedback context changes.","Multi-window isolation is claimed; ensure the correct project_directory is provided when running across multiple Cursor windows."]}}