Planexe
MCP server for generating rough-draft project plans from natural-language prompts.
What is Planexe?
Planexe is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for generating rough-draft project plans from natural-language prompts.
MCP server for generating rough-draft project plans from natural-language prompts.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server for generating rough-draft project plans from nat
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx planexeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Planexe
PlanExe is an MCP server that turns a short natural-language idea into a detailed, multi-page project plan in roughly 15 minutes. It uses LLM pipelines (via OpenRouter, Ollama, or LM Studio) and PDDL-based planning to produce structured work-breakdown structures, feasibility assessments, and task hierarchies. Developers, product managers, and researchers use it to rapidly scaffold complex project plans without manual document writing.
Prerequisites
- An OpenRouter account with a funded API key (or a local Ollama/LM Studio instance as an alternative)
- A PlanExe account at home.planexe.org if using the hosted cloud MCP endpoint
- Docker and Docker Compose (recommended) OR Python 3.10+ for local runs
- An MCP-compatible client such as Claude Desktop or Claude Code
Create a PlanExe account and obtain credentials
Sign up at home.planexe.org to get a PlanExe API key (format: pex_...). If you prefer a fully local setup, you will use OpenRouter or Ollama instead and can skip cloud account creation.
Set up your LLM backend
PlanExe calls an LLM to generate plans. The easiest path is an OpenRouter API key. Alternatively, install and run Ollama locally with a capable model.
# Option A: export your OpenRouter key
export OPENROUTER_API_KEY="sk-or-..."
# Option B: start Ollama with a capable model
ollama serve
ollama pull llama3.1:70bRun PlanExe via Docker Compose (recommended)
Clone the repository and bring up the worker and frontend services. Copy the example env file first and fill in your API keys.
git clone https://github.com/PlanExeOrg/PlanExe.git
cd PlanExe
cp .env.docker-example .env
# Edit .env and set OPENROUTER_API_KEY
docker compose up worker_plan frontend_multi_userAdd PlanExe to your MCP client configuration
Point your MCP client at the hosted cloud endpoint using your PlanExe API key. The remote MCP URL is https://mcp.planexe.org/mcp and requires the X-API-Key header.
Test the server by creating a sample plan
Use the plan_create tool in your MCP client with a short natural-language description of your project idea. Poll plan_status until the plan is complete, then retrieve results with plan_file_info.
Planexe Examples
Client configuration
Connect to the hosted PlanExe MCP endpoint. Replace the X-API-Key value with your pex_... key from the dashboard.
{
"mcpServers": {
"planexe": {
"command": "npx",
"args": ["planexe"],
"env": {
"OPENROUTER_API_KEY": "sk-or-your-key-here"
}
}
}
}Prompts to try
After connecting, ask Claude to use PlanExe's tools to build a project plan.
- "Use PlanExe to create a project plan for building a B2B SaaS invoicing platform"
- "Generate a rough-draft plan for launching a community podcast in 90 days"
- "Create a work-breakdown structure for migrating a monolith to microservices"
- "Show me the example plans available in PlanExe"
- "Check the status of my latest PlanExe plan"Troubleshooting Planexe
plan_create returns an error about missing LLM credentials
Ensure OPENROUTER_API_KEY is set in your environment or .env file. If using Ollama, confirm the server is running on localhost:11434 and the model you selected with model_profiles is actually pulled.
Plan generation takes much longer than expected or hangs
Full plans can take 10-20 minutes. Use plan_status to poll progress. If it is stuck, try plan_retry. Lightweight models (e.g. mistral-7b) produce faster but shallower plans than GPT-4-class models.
Docker Compose services exit immediately on startup
Check that your .env file exists and contains valid values (OPENROUTER_API_KEY at minimum). Run `docker compose logs worker_plan` to see the specific error.
Frequently Asked Questions about Planexe
What is Planexe?
Planexe is a Model Context Protocol (MCP) server that mcp server for generating rough-draft project plans from natural-language prompts. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Planexe?
Follow the installation instructions on the Planexe GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Planexe?
Planexe works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Planexe free to use?
Yes, Planexe is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Planexe Alternatives — Similar Coding Agents Servers
Looking for alternatives to Planexe? 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 Planexe 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 Planexe?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.