Sub-Agents
Delegates tasks to specialized AI assistants in Cursor and Claude Code CLI tools by automatically di...
Create Your Agents Folder
- Make a new folder somewhere on your computer for your agents.
- Example (Mac/Linux):
/Users/yourname/my-agents - Example (Windows):
C:\Users\yourname\my-agents - Do not use a relative path like
./agents—it must be absolute.
Add Agent Files
- In your agents folder, add
.mdor.txtfiles for each specialized agent. - Example:
code-reviewer.md# Code Reviewer You are a specialized AI assistant that reviews code, finds bugs, and checks quality. - The filename (without extension) is the agent’s name.
- In your agents folder, add
Collect Required ENV Values
- You will need to set:
AGENTS_DIR– The absolute path to your agents folder.AGENT_TYPE– Set to eithercursororclaudedepending on your AI tool.
- You will need to set:
Enter ENV Values in FastMCP
- In the FastMCP connection interface, click the "Install Now" button to open the environment variables form.
- Fill in the following values:
- AGENTS_DIR: The absolute path to your agents folder (from step 1).
- AGENT_TYPE:
cursor(for Cursor) orclaude(for Claude Code).
Optional: Set Execution Timeout
- If you need to change the agent execution time, you may add the optional variable:
- EXECUTION_TIMEOUT_MS: Time in milliseconds (e.g.,
600000for 10 minutes).
- EXECUTION_TIMEOUT_MS: Time in milliseconds (e.g.,
- If you need to change the agent execution time, you may add the optional variable:
Finish Setup
- Complete the configuration and restart your IDE or tool if necessary.
- Your specialized agents are ready for use via MCP.
Quick Start
Choose Connection Type for
Authentication Required
Please sign in to use FastMCP hosted connections
Configure Environment Variables for
Please provide values for the following environment variables:
started!
The MCP server should open in . If it doesn't open automatically, please check that you have the application installed.
Copy and run this command in your terminal:
Make sure Gemini CLI is installed:
Visit Gemini CLI documentation for installation instructions.
Make sure Claude Code is installed:
Visit Claude Code documentation for installation instructions.
Installation Steps:
Configuration
Installation Failed
More for Developer Tools
View All →
GitHub
Remote
Extend your developer tools with the GitHub MCP Server—a powerful Model Context Protocol server enhancing automation and AI interactions with GitHub APIs. It supports diverse functionalities like managing workflows, issues, pull requests, repositories, and security alerts. Customize available toolsets to fit your needs, enable dynamic tool discovery to streamline tool usage, and run the server locally or remotely. With read-only mode and support for GitHub Enterprise, this server integrates deeply into your GitHub ecosystem, empowering data extraction and intelligent operations for developers and AI applications. Licensed under MIT, it fosters flexible and advanced GitHub automation.
Desktop Commander
Desktop Commander MCP transforms Claude Desktop into a powerful AI assistant for managing files, running terminal commands, and editing code with precision across your entire system. It supports in-memory code execution, interactive process control, advanced search and replace, plus comprehensive filesystem operations including reading from URLs and negative offset file reads. With detailed audit and fuzzy search logging, it enables efficient automation, data analysis, and multi-project workflows—all without extra API costs. Designed for developers seeking smarter automation, it enhances productivity by integrating all essential development tools into a single, intelligent chat interface.
Figma Context
Unlock seamless design-to-code with Framelink Figma MCP Server, letting AI coding tools access your Figma files directly. It simplifies Figma API data to supply only relevant design layouts and styles, boosting AI accuracy in implementing designs across frameworks. Specifically built for use with tools like Cursor, it transforms design metadata into precise code in one step. This server streamlines the workflow by providing clean, focused context, enabling faster and more reliable design-driven development. Enjoy a powerful bridge between design and coding that enhances productivity and code quality with minimal fuss.
Chrome DevTools
Provides direct Chrome browser control through DevTools for web automation, debugging, and performance analysis using accessibility tree snapshots for reliable element targeting, automatic page event handling, and integrated performance tracing with actionable insights.
Microsoft Docs
Remote
Access official Microsoft documentation instantly with the Microsoft Learn Docs MCP Server. This cloud service implements the Model Context Protocol (MCP) to enable AI tools like GitHub Copilot and others to perform high-quality semantic searches across Microsoft Learn, Azure, Microsoft 365 docs, and more. It delivers up to 10 concise, context-relevant content chunks in real time, ensuring up-to-date, accurate information. Designed for seamless integration with any MCP-compatible client, it helps AI assistants ground their responses in authoritative, current Microsoft resources for better developer support and productivity.
Similar MCP Servers
A2AMCP
Coordinates multiple AI agents working on shared codebases through Redis-backed infrastructure that provides real-time messaging, file locking to prevent simultaneous edits, interface sharing for type definitions, and distributed task management across parallel development sessions.