Skip to main content
Glama
ISimon3

Interactive Feedback MCP

by ISimon3
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

🗣️ Interactive Feedback MCP

Simple MCP Server to enable a human-in-the-loop workflow in AI-assisted development tools like Cursor, Cline and Windsurf. This server allows you to easily provide feedback directly to the AI agent, bridging the gap between AI and you.

Note: This server is designed to run locally alongside the MCP client (e.g., Claude Desktop, VS Code), as it needs direct access to the user's operating system to display notifications.

🖼️ Example

Interactive Feedback Example

Related MCP server: Interactive Feedback MCP

💡 Why Use This?

In environments like Cursor, every prompt you send to the LLM is treated as a distinct request — and each one counts against your monthly limit (e.g. 500 premium requests). This becomes inefficient when you're iterating on vague instructions or correcting misunderstood output, as each follow-up clarification triggers a full new request.

This MCP server introduces a workaround: it allows the model to pause and request clarification before finalizing the response. Instead of completing the request, the model triggers a tool call (interactive_feedback) that opens an interactive feedback window. You can then provide more detail or ask for changes — and the model continues the session, all within a single request.

Under the hood, it's just a clever use of tool calls to defer the completion of the request. Since tool calls don't count as separate premium interactions, you can loop through multiple feedback cycles without consuming additional requests.

Essentially, this helps your AI assistant ask for clarification instead of guessing, without wasting another request. That means fewer wrong answers, better performance, and less wasted API usage.

  • 💰 Reduced Premium API Calls: Avoid wasting expensive API calls generating code based on guesswork.

  • ✅ Fewer Errors: Clarification _before_ action means less incorrect code and wasted time.

  • ⏱️ Faster Cycles: Quick confirmations beat debugging wrong guesses.

  • 🎮 Better Collaboration: Turns one-way instructions into a dialogue, keeping you in control.

🛠️ Tools

This server exposes the following tool via the Model Context Protocol (MCP):

  • interactive_feedback: Asks the user a question and returns their answer. Can display predefined options.

📦 Installation

  1. Prerequisites:

    • Python 3.11 or newer.

    • uv (Python package manager). Install it with:

      • Windows: pip install uv

      • Linux: curl -LsSf https://astral.sh/uv/install.sh | sh

      • macOS: brew install uv

  2. Get the code:

    • Clone this repository: git clone https://github.com/pauoliva/interactive-feedback-mcp.git

    • Or download the source code.

⚙️ Configuration

  1. Add the following configuration to your claude_desktop_config.json (Claude Desktop) or mcp.json (Cursor): Remember to change the /path/to/interactive-feedback-mcp path to the actual path where you cloned the repository on your system.

{
  "mcpServers": {
    "interactive-feedback": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/interactive-feedback-mcp",
        "run",
        "server.py"
      ],
      "timeout": 600,
      "autoApprove": [
        "interactive_feedback"
      ]
    }
  }
}

  1. Add the following to the custom rules in your AI assistant (in Cursor Settings > Rules > User Rules):

If requirements or instructions are unclear use the tool interactive_feedback to ask clarifying questions to the user before proceeding, do not make assumptions. Whenever possible, present the user with predefined options through the interactive_feedback MCP tool to facilitate quick decisions.

Whenever you're about to complete a user request, call the interactive_feedback tool to request user feedback before ending the process. If the feedback is empty you can end the request and don't call the tool in loop.

This will ensure your AI assistant always uses this MCP server to request user feedback when the prompt is unclear and before marking the task as completed.

Available Tools

1 tool
interactive_feedbackC

向用户请求交互式反馈，支持文本和图片

ParametersJSON Schema
NameRequiredDescriptionDefault
messageYes向用户提出的具体问题
predefined_optionsNo提供给用户选择的预定义选项（可选）

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that the tool '支持文本和图片' (supports text and images), which adds some context about input types. However, it does not describe critical behavioral traits such as whether this is a blocking operation, how feedback is collected or returned, error handling, or any permissions required. For a tool with no annotations, this leaves significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise and front-loaded: '向用户请求交互式反馈，支持文本和图片' (Request interactive feedback from users, supporting text and images). It is a single sentence with no wasted words, clearly stating the core functionality. Every part of the description earns its place by specifying the action and supported formats.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a feedback collection tool with no annotations and no output schema, the description is incomplete. It lacks information about how the feedback is returned (e.g., format, structure), any side effects, or error conditions. While it mentions support for text and images, it does not cover the full behavioral context needed for an agent to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, meaning both parameters ('message' and 'predefined_options') are fully documented in the schema. The description does not add any additional meaning or clarification beyond what the schema provides (e.g., it does not explain how 'predefined_options' should be formatted or used). With high schema coverage, the baseline score of 3 is appropriate as the description does not compensate but also does not detract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '向用户请求交互式反馈，支持文本和图片' (Request interactive feedback from users, supporting text and images). It specifies the verb ('请求' - request) and resource ('交互式反馈' - interactive feedback) with additional detail about supported input types. However, since there are no sibling tools, it cannot demonstrate differentiation from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or contextual factors that would help an agent decide when this tool is appropriate. The absence of sibling tools means no explicit alternatives are named, but general usage context is still missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as requesting interactive feedback with support for text and images, and no other tools exist to cause confusion.

Naming Consistency5/5

The single tool name 'interactive_feedback' follows a clear and consistent snake_case pattern. Since there is only one tool, there is no inconsistency to evaluate, and the naming is straightforward and descriptive.

Tool Count2/5

A single tool is too few for a server named 'Interactive Feedback MCP', which suggests a broader scope for interactive feedback mechanisms. This minimal set may limit functionality and force agents to rely heavily on this one tool for all feedback-related tasks, which is insufficient for typical MCP server purposes.

Completeness2/5

The tool surface is severely incomplete for an interactive feedback domain. While 'interactive_feedback' handles requesting feedback, there are obvious gaps such as tools for managing feedback (e.g., list, update, delete), analyzing feedback, or supporting other feedback types beyond text and images. This will likely cause agent failures in comprehensive feedback workflows.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Copilot Leecher

    xiangxiaobo
    F
    license
    A
    quality
    Not graded
    maintenance
    An MCP server that enables users to review and refine AI outputs through a local web UI, returning feedback as free tool call results to save on GitHub Copilot premium requests. It allows for multiple rounds of iterative improvements within a single request session.
    1
    30

  • mowan-mcp-feedback

    limowan
    F
    license
    A
    quality
    C
    maintenance
    An interactive feedback MCP server with a web UI, enabling AI-driven development workflows where AI can prompt users for feedback before taking actions, supporting platforms like Cursor, Cline, and Windsurf.
    2

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ISimon3/interactive-feedback-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server