Interactive Feedback
Interactive Feedback MCP provides a human-in-the-loop interface for AI-assisted development tools like Cursor, Cline, and Windsurf, enabling users to execute commands, view outputs, and provide textual feedback directly to the AI during development tasks. The server supplies tools that allow AI assistants to pause before task completion and request user feedback, reducing speculative tool calls and consolidating multiple operations into single, feedback-aware requests. It solves the problem of inefficient AI-assisted workflows by promoting iterative collaboration rather than autonomous completion, potentially reducing premium API calls by up to 25 times in some scenarios.
- GitHub stars
- 1.7K
- tool
- 1
- last updated
- Mar 10, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
interactive_feedbackLets the AI assistant request user feedback, with the project directory and a summary of the completed work passed as arguments.
Lets the AI assistant request user feedback, with the project directory and a summary of the completed work passed as arguments.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Interactive Feedback MCP
Developed by Fábio Ferreira (@fabiomlferreira). Check out dotcursorrules.com for more AI development enhancements.
Simple MCP Server to enable a human-in-the-loop workflow in AI-assisted development tools like Cursor. This server allows you to run commands, view their output, and provide textual feedback directly to the AI. It is also compatible with Cline and Windsurf.
Prompt Engineering
For the best results, add the following to your custom prompt in your AI assistant, you should add it on a rule or directly in the prompt (e.g., Cursor):