Ck Ask
CK-ASK is an AI conversation pause tool that bypasses MCP restrictions through pure HTTP communication, provides dual modes (terminal and pop-up window) to wait for user input, and supports file upload and automatic callback.
rating : 2.5 points
downloads : 6.1K
What is CK-ASK?
CK-ASK is an AI conversation pause tool specifically designed to pause the execution process of the AI assistant (such as the AI in Windsurf and Cursor) when it needs user confirmation, additional information, or decision-making during task execution. It's like a 'pause button' between the AI and the user, enabling better collaboration between the AI and the user.How to use CK-ASK?
Using CK-ASK is very simple: when the AI assistant reaches a step that requires your intervention, CK-ASK will automatically trigger a pause and display a prompt message through a pop-up window or the terminal. You just need to enter instructions, confirm operations, or provide the required files according to the prompt, and the AI will continue to execute subsequent tasks based on your input. The entire process does not require manual configuration of complex communication protocols.Applicable Scenarios
CK-ASK is particularly suitable for the following scenarios: 1. Code review and modification confirmation: After the AI completes code modification, it waits for you to confirm whether to continue optimization. 2. File processing decision: The AI needs you to select the file to be processed or specify the processing method. 3. Content creation guidance: After the AI generates content, it waits for your feedback and further instructions. 4. Multi-step task coordination: Obtain user instructions in segments during complex tasks.Main Features
Bypass MCP Restrictions
It uses a pure HTTP communication method, eliminating the need to configure the complex Model Context Protocol (MCP), which simplifies the integration and usage process.
Dual-Mode Interaction
It supports two interaction methods: terminal mode and pop-up window mode. The terminal mode is suitable for direct operation by developers, and the pop-up window mode provides a more user-friendly graphical interface.
File Upload Support
When pausing and waiting, it supports users to upload pictures and other files as additional information to help the AI better understand task requirements.
Automatic Callback Mechanism
The intelligent port discovery and automatic callback functions ensure that the AI can continue to execute seamlessly after user input, without manual intervention in the communication process.
Independent Operation Capability
It can run as an independent tool, without relying on a specific AI platform or editor, and has good universality and portability.
Advantages
Simple configuration: Compared with traditional MCP solutions, CK-ASK does not require complex configuration and can be used out of the box.
Reliable communication: Based on the HTTP protocol, the communication is stable and easy to debug.
Flexible interaction: It provides two modes, terminal and pop-up window, to adapt to different user preferences.
Independent operation: It does not rely on a specific platform and can be used in various AI assistant environments.
Easy to integrate: The simple API interface facilitates integration with other tools.
Limitations
Requires network connection: Based on HTTP communication, it requires local network environment support.
Port occupation: It will occupy local ports during operation, which may conflict with existing services.
Depends on Node.js environment: The core script requires a Node.js runtime environment.
Pop-up window mode requires extension: A beautiful pop-up window interface requires the installation of a VSIX extension.
Learning cost: New users need to understand basic terminal operations or extension installation.
How to Use
Choose the Installation Method
Choose the installation method according to your needs:
- For simple use: Use the Node.js script directly.
- For full functionality: Install the VSIX extension to get a pop-up window interface.
- For developers: Use it with the Python MCP Server.
Run CK-ASK
Start the CK-ASK service, and it will automatically listen on the specified port and wait for calls from the AI assistant.
Interact with the AI Assistant
When the AI assistant needs your input, CK-ASK will automatically trigger a pause and display a prompt message waiting for your instructions.
Provide Input and Continue
Enter instructions, confirm operations, or upload files according to the prompt, and the AI assistant will continue to execute the task based on your input.
Usage Examples
Code Review and Optimization
After the AI assistant completes code modification, it pauses and waits for the user to review the modified content and decide the next operation.
File Selection and Processing
The AI assistant finds relevant content in multiple files and pauses to wait for the user to select the file to be processed.
Content Creation Guidance
After the AI generates preliminary content, it pauses and waits for the user to provide feedback and further creation directions.
Frequently Asked Questions
What is the difference between CK-ASK and the traditional MCP solution?
What dependencies do I need to install to use CK-ASK?
Which AI assistants or editors does CK-ASK support?
How to solve the port conflict problem?
Does CK-ASK support team collaboration scenarios?
Related Resources
GitHub Project Repository
The complete source code, documentation, and latest version of CK-ASK
Node.js Official Website
Download and documentation for the Node.js runtime environment
Windsurf Editor
One of the AI code editors that support CK-ASK
Cursor Editor
Another AI code editor that supports CK-ASK
MCP Protocol Documentation
Official specification documentation for the Model Context Protocol

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
24.5K
4.5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
27.9K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
82.1K
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
38.8K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
71.9K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
37.8K
5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.5K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
56.4K
4.8 points





