DecisionNode
📇 🏠 🍎 🪟 🐧 - Record development decisions as structured JSON, embed as vectors v
What is DecisionNode?
DecisionNode is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 📇 🏠 🍎 🪟 🐧 - record development decisions as structured json, embed as vectors v
📇 🏠 🍎 🪟 🐧 - Record development decisions as structured JSON, embed as vectors v
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP protocol support
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx decisionnode-decisionnodeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use DecisionNode
DecisionNode is a developer tool for recording, searching, and managing architectural and development decisions as structured JSON with vector embeddings. It exposes nine MCP tools that allow AI coding assistants like Claude Code and Cursor to search past decisions before generating code, add new decisions interactively, update or deprecate existing entries, and track the full history of choices made in a project. This prevents AI from repeating rejected approaches and ensures consistency across a codebase over time.
Prerequisites
- Node.js 18+ and npm installed
- A free Gemini API key (for gemini-embedding-001 vector embeddings) obtained from Google AI Studio
- An MCP-compatible client such as Claude Code or Cursor
- Git repository in the project where you want to track decisions
Install the DecisionNode CLI globally
Install the decisionnode package globally so the decide command is available system-wide.
npm install -g decisionnodeInitialize a decision store in your project
Run decide init in your project root to create the local decision store. This sets up the storage structure under ~/.decisionnode/.
cd your-project
decide initConfigure your Gemini API key
Run decide setup to provide your Gemini API key. This is required for generating vector embeddings that power semantic search.
decide setupRegister the MCP server with Claude Code
Add the decide-mcp server to Claude Code at user scope so it is available across all your projects.
claude mcp add decisionnode -s user decide-mcpRecord your first decision
Use the decide add command to record an architectural decision with a section and description. These become searchable via both the CLI and the MCP tools.
decide add -s Backend -d "Skipped connection pooling for embeddings DB due to low query volume"Search decisions from the CLI to verify
Test semantic search to confirm embeddings are working and your decision was stored correctly.
decide search "connection pooling"DecisionNode Examples
Client configuration
Claude Desktop configuration for the DecisionNode MCP server using the globally installed decide-mcp command.
{
"mcpServers": {
"decisionnode": {
"command": "decide-mcp",
"args": []
}
}
}Prompts to try
Example prompts for the AI assistant to interact with your decision store via MCP tools.
- "Search decisions about authentication before writing the login module"
- "Add a decision: we chose PostgreSQL over MongoDB for relational data integrity"
- "List all decisions in the Backend section"
- "Has a decision been made about caching strategy?"
- "Mark the Redis caching decision as deprecated"Troubleshooting DecisionNode
Embedding generation fails with API error
Verify your Gemini API key is valid and was entered correctly during decide setup. Retrieve a key from https://aistudio.google.com/app/apikey — the free tier is sufficient for most usage.
decide-mcp command not found in Claude Code
Ensure you ran npm install -g decisionnode and that the global npm bin directory is in PATH. Run which decide to confirm, then rerun claude mcp add decisionnode -s user decide-mcp.
Search returns irrelevant results
Adjust the similarity threshold with decide search --threshold 0.5 (default is 0.3). A higher value returns only close matches. Also ensure the decision text is descriptive enough for the embedding model.
Frequently Asked Questions about DecisionNode
What is DecisionNode?
DecisionNode is a Model Context Protocol (MCP) server that 📇 🏠 🍎 🪟 🐧 - record development decisions as structured json, embed as vectors v It connects AI assistants to external tools and data sources through a standardized interface.
How do I install DecisionNode?
Follow the installation instructions on the DecisionNode GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with DecisionNode?
DecisionNode works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is DecisionNode free to use?
Yes, DecisionNode is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
DecisionNode Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to DecisionNode? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up DecisionNode 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 DecisionNode?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.