Persistent AI agent brain MCP server providing embedded coding standards, automatic stack detection, and project memory that survives across conversations, with tools for retrieving standards, detecting tech stacks, saving/retrieving project context, and validating code.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
dev-brain-mcp
Your AI agent's persistent brain. Coding standards that never get forgotten, stack detection, and project memory that survives across conversations.
Inspired by ponytail, codebase-memory-mcp, and Graft.
The Problem
AI coding agents forget your rules in long conversations. Skills and instructions get truncated from the context window after many iterations. This MCP server solves that by:
Embedding rules in tool descriptions — tool descriptions live in the system prompt and NEVER get truncated
Detecting your stack automatically — no need to tell the agent "this is a React + RTK project" every time
Persistent project memory — notes, architectural decisions, and conventions survive across conversations
Related MCP server: databricks-mcp-server
Install
git clone https://github.com/YOUR_USERNAME/dev-brain-mcp.git
cd dev-brain-mcp
npm installSetup in Antigravity 2.0
Global Configuration (recommended)
Go to Settings → MCP Servers and add:
{
"mcpServers": {
"dev-brain": {
"command": "node",
"args": ["C:/Users/david/Documents/dev-brain-mcp/server.js"]
}
}
}⚠️ Update the path to wherever you cloned this repo.
Per-Project Configuration
Create .agents/mcp.json in your project root:
{
"mcpServers": {
"dev-brain": {
"command": "node",
"args": ["C:/path/to/dev-brain-mcp/server.js"]
}
}
}Other Agents (Claude Code, Cursor, etc.)
Add to your MCP config:
{
"mcpServers": {
"dev-brain": {
"command": "node",
"args": ["/path/to/dev-brain-mcp/server.js"]
}
}
}Tools
Tool | Description | When to use |
| Returns ponytail rules + stack-specific rules | Before writing code |
| Detects language, framework, dependencies | Start of every session |
| Retrieves persistent notes, decisions, conventions | Start of every conversation |
| Saves context that survives across sessions | After learning something important |
| Checks code against standards | After writing code |
| Lists all previously analyzed projects | When switching projects |
Why It Works
Skills (ponytail, RTK rules):
→ Instructions read into conversation context
→ Get TRUNCATED after ~30 iterations
→ Agent forgets them completely ❌
MCP Tool Descriptions:
→ Live in the system prompt alongside tool definitions
→ NEVER get truncated, no matter how long the conversation
→ Agent always sees them ✅
Persistent Memory (projects.json):
→ Stored on disk, survives across conversations
→ Agent retrieves context at start of each session
→ No re-exploration needed ✅Adding Your Own Rules
Edit lib/rules.js:
Universal rules: Add to
UNIVERSAL_RULES.principlesStack-specific rules: Add a new key to
CONDITIONAL_RULESValidation checks: Add patterns to
validateCode()
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.
Related MCP Servers
- -
- MIT
- -
- FlicenseNot gradedqualityDmaintenanceProjectBrain MCP is a Model Context Protocol (MCP) server for project planning and execution workflows. It exposes tools for tasks, decisions, facts, milestones, comments, and team messaging through a Streamable HTTP endpoint.-