Cursor Cloud Agent MCP
C

Cursor Cloud Agent MCP

This is an MCP server developed for the Cursor cloud agent API, which allows AI assistants to create and manage cloud agent tasks on GitHub repositories, providing functions such as task creation, status monitoring, and viewing conversation history.
2.5 points
9.6K

What is the Cursor Cloud Agent MCP Server?

This is a Model Context Protocol (MCP) server specifically designed to connect AI assistants (such as Cursor, Claude, etc.) with Cursor's cloud agent API. It allows AI assistants to perform automated tasks on GitHub repositories, such as: - Automatically write and modify code - Create documents and README files - Fix bugs and implement new features - Automatically create Pull Requests In essence, it gives AI assistants the 'ability to act' and directly perform tasks in the code repository.

How to use the Cursor Cloud Agent MCP Server?

The usage process is divided into three main steps: 1. **Installation and Configuration**: Install the server via npm and configure the API key. 2. **Connect the AI Assistant**: Configure the MCP connection in Cursor or Claude Desktop. 3. **Send Tasks**: The AI assistant creates and manages cloud agent tasks through the tool. The AI assistant can detect the current GitHub repository, create tasks, monitor progress, and view results.

Use Cases

This tool is particularly suitable for the following scenarios: - **Automated Code Maintenance**: Automatically update dependencies and fix security vulnerabilities. - **Documentation Generation**: Automatically generate or update documentation for the project. - **Feature Development**: Implement small features or fix bugs. - **Code Refactoring**: Improve the code structure and quality. - **Test Coverage**: Add test cases. - **CI/CD Optimization**: Improve build and deployment scripts.

Main Features

GitHub Repository Detection
Automatically detect information about the current GitHub repository, including the repository URL, branch status, and uncommitted changes. The AI assistant can create tasks based on the current working environment.
Cloud Agent Task Management
Create, monitor, and manage cloud agent tasks. Support task status tracking (creating, running, completed, etc.), and view the progress at any time.
Automatic Pull Request
Automatically create a GitHub Pull Request after the task is completed, facilitating code review and merging. You can specify the branch name and PR settings.
Task Follow - up
Send additional instructions during the task execution process to guide the agent to complete more complex multi - step tasks.
View Conversation History
View the complete conversation history between the AI agent and the system to understand the specific process and decision - making basis of task execution.
Parallel Task Planning
Decompose large - scale projects into multiple independent tasks that can be executed in parallel to improve efficiency. The system will automatically analyze task dependencies.
Multi - Model Support
Support multiple AI models (such as Claude - 4 - Sonnet - Thinking, o3, etc.), and select the appropriate model according to task requirements.
Flexible Deployment Options
Support two operating modes: HTTP server and Stdio server, facilitating integration and use in different environments.
Advantages
High degree of automation: AI can fully autonomously execute code modification tasks.
Seamless integration with GitHub: Directly operate the repository and automatically create PRs.
Transparent task status: Real - time monitoring of task progress and status.
Support for complex tasks: Support multi - step tasks through follow - up instructions.
Parallel processing capability: Plan parallel tasks to improve efficiency.
Easy to integrate: Support multiple AI assistants (Cursor, Claude, etc.).
Limitations
Requires an API key: Must have access to the Cursor Cloud Agents API.
GitHub dependency: Only supports GitHub repositories and does not support other code hosting platforms.
Rate limit: There are strict API call limits when retrieving all repositories.
Learning curve: Need to understand the MCP protocol and configuration methods.
Network dependency: Requires a stable network connection to access the API.
Cost consideration: Using the cloud agent service may incur fees.

How to Use

Install the MCP Server
Install the MCP server globally or locally via npm.
Set the API Key
Obtain the Cursor API key and set it as an environment variable.
Configure the AI Assistant
Configure the MCP server connection in Cursor or Claude Desktop.
Start Using
The AI assistant can now use various tools to manage cloud agent tasks.

Usage Examples

Automatic Documentation Generation
Automatically create a complete README document for the project, including installation instructions, usage examples, and API documentation.
Code Security Fix
Automatically scan and fix security vulnerabilities in the code, such as dependency vulnerabilities or sensitive information leakage.
Feature Implementation
Implement a new functional module according to the requirement description.
Code Refactoring
Improve the structure and quality of the existing code to enhance maintainability.

Frequently Asked Questions

What do I need to use this MCP server?
Is this service free?
Which GitHub repositories are supported?
How long does task execution take?
How can I ensure that AI does not damage my code?
Can I cancel a task?
Does it support team collaboration?
How can I get help if I encounter problems?

Related Resources

GitHub Repository
The project's source code and latest version.
Cursor Cloud Agents API Documentation
Official API documentation and interface descriptions.
Model Context Protocol Specification
Technical specifications and standards for the MCP protocol.
npm Package Page
Package information and installation instructions on npm.
Cursor Official Website
The official website of the Cursor AI code editor.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "cursor-cloud-agent": {
      "command": "npx",
      "args": ["-y", "cursor-cloud-agent-mcp"],
      "env": {
        "CURSOR_API_KEY": "${env:CURSOR_API_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "cursor-cloud-agent": {
      "command": "cursor-cloud-agent-mcp",
      "env": {
        "CURSOR_API_KEY": "${env:CURSOR_API_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "cursor-cloud-agent": {
      "command": "npm",
      "args": ["run", "start:stdio"],
      "env": {
        "CURSOR_API_KEY": "${env:CURSOR_API_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "cursor-cloud-agent": {
      "url": "http://localhost:3000/mcp",
      "headers": {}
    }
  }
}

{
  "mcpServers": {
    "cloud-agent": {
      "type": "http",
      "url": "http://localhost:3000/mcp"
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
10.1K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.6K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
14.5K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
7.5K
4 points
P
Paperbanana
Python
8.6K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
10.2K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
9.5K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
9.2K
5 points
N
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
24.3K
4.5 points
M
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
37.3K
5 points
G
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
26.6K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
78.8K
4.3 points
U
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
F
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
70.8K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
104.7K
4.7 points
G
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
24.4K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase