SystemPrompt Coding Agent
An MCP server that orchestrates AI coding assistants (Claude Code CLI and Gemini CLI) to perform complex programming tasks autonomously, allowing remote control of your local development environment from anywhere.
What is SystemPrompt Coding Agent?
SystemPrompt Coding Agent is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that orchestrates ai coding assistants (claude code cli and gemini cli) to perform complex programming tasks autonomously, allowing remote control of your local development environment from...
An MCP server that orchestrates AI coding assistants (Claude Code CLI and Gemini CLI) to perform complex programming tasks autonomously, allowing remote control of your local development environment from anywhere.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server that orchestrates AI coding assistants (Claude
Use Cases
Maintainer
Works with
Installation
NPM
npx -y systemprompt-coding-agentManual Installation
npx -y systemprompt-coding-agentConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use SystemPrompt Coding Agent
SystemPrompt Coding Agent is an MCP server that orchestrates AI coding assistants — including Claude Code CLI and Gemini CLI — to autonomously perform complex programming tasks on your local development environment. It runs as a Dockerized service with optional Cloudflare tunnel support, letting you issue coding tasks remotely from any MCP-compatible client. The server exposes task lifecycle tools to create, update, monitor, and finalize multi-step coding sessions, effectively turning your laptop into a remotely accessible AI coding agent.
Prerequisites
- Node.js 18 or higher
- Docker and Docker Compose installed and running
- Claude Code CLI installed (optional but recommended for best results)
- An MCP-compatible client such as Claude Desktop
- A Cloudflare account with tunnel token if you want remote access from outside your local network
Clone the repository
Clone the systemprompt-code-orchestrator repository to your local machine where your code projects live.
git clone https://github.com/systempromptio/systemprompt-code-orchestrator
cd systemprompt-code-orchestratorInstall dependencies and run the setup wizard
Install npm dependencies and run the interactive setup script. The wizard verifies your Node.js version, Docker installation, and prompts for your PROJECT_ROOT path where AI agents will have write access.
npm i
npm run setupSet required environment variables
Set the PROJECT_ROOT environment variable to the directory where your code lives. This is the workspace AI agents will operate in. Optionally set CLOUDFLARE_TOKEN for tunnel access.
export PROJECT_ROOT=/path/to/your/code
export PORT=3000
# Optional: export CLOUDFLARE_TOKEN=your-token-hereStart all services
Launch the full stack using the npm start command, which brings up all Docker containers including the MCP server, task orchestrator, and any configured tunnels.
npm run startConfigure your MCP client
Add the systemprompt-coding-agent to your Claude Desktop configuration. The server runs via npx for a zero-install experience.
{
"mcpServers": {
"systemprompt-coding-agent": {
"command": "npx",
"args": ["-y", "systemprompt-coding-agent"],
"env": {
"PROJECT_ROOT": "/path/to/your/code"
}
}
}
}Verify the agent is reachable
Run the status check command to confirm all services are healthy and the AI coding agents (Claude Code, Gemini CLI) are detected and ready.
npm run statusSystemPrompt Coding Agent Examples
Client configuration (Claude Desktop)
claude_desktop_config.json entry for the SystemPrompt Coding Agent using npx.
{
"mcpServers": {
"systemprompt-coding-agent": {
"command": "npx",
"args": ["-y", "systemprompt-coding-agent"],
"env": {
"PROJECT_ROOT": "/Users/yourname/projects",
"PORT": "3000"
}
}
}
}Prompts to try
Example prompts that drive the coding agent to perform autonomous development tasks.
- "Create a task to fix the bug where login fails after password reset — the error is 401 Unauthorized at auth.js line 42."
- "Start a new coding session to add unit tests for the UserService class in my project."
- "Check the status of all current AI coding tasks and report what's in progress."
- "Update the running task to also refactor the database connection pooling while it's working on auth."
- "End the current coding task and generate a structured report of all changes made."Troubleshooting SystemPrompt Coding Agent
Docker containers fail to start
Ensure Docker Desktop is running before executing `npm run start`. Run `npm run logs` to see detailed container startup errors. Verify Docker Compose is installed with `docker compose version`.
AI agents cannot find or modify files
Check that PROJECT_ROOT is set to an absolute path that exists and is readable/writable. The path must be accessible inside Docker containers — avoid paths with symlinks or special mounts.
Remote access via tunnel not working
Ensure CLOUDFLARE_TOKEN is set correctly and that you have an active Cloudflare tunnel configured. Run `npm run tunnel` separately to debug tunnel connectivity before starting the full stack.
Frequently Asked Questions about SystemPrompt Coding Agent
What is SystemPrompt Coding Agent?
SystemPrompt Coding Agent is a Model Context Protocol (MCP) server that mcp server that orchestrates ai coding assistants (claude code cli and gemini cli) to perform complex programming tasks autonomously, allowing remote control of your local development environment from anywhere. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install SystemPrompt Coding Agent?
Install via npm with the command: npx -y systemprompt-coding-agent. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with SystemPrompt Coding Agent?
SystemPrompt Coding Agent works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is SystemPrompt Coding Agent free to use?
Yes, SystemPrompt Coding Agent is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
SystemPrompt Coding Agent Alternatives — Similar Coding Agents Servers
Looking for alternatives to SystemPrompt Coding Agent? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up SystemPrompt Coding Agent in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use SystemPrompt Coding Agent?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.