project-brain-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@project-brain-mcpget context for my current project to review past decisions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Project Brain MCP
Engineering memory for Claude Code — prevents re-investigating solved problems and repeating rejected architectural decisions across sessions and projects.
What it does
Prevent re-investigating: Answered questions are recorded as findings. Future sessions skip re-investigation.
Prevent repeating rejected architectures:
validate_planchecks your proposal against past decisions and mistakes before you proceed.Cross-project learning: Decisions from other projects appear as soft references, not hard blocks.
Persistent memory: Survives across sessions, stored in
~/.project-brain/memory.json.
Related MCP server: Cortex
Installation
pip install git+https://github.com/pym2282/project-brain-mcp
claude mcp add project-brain project-brain-mcp --scope userRestart Claude Code. The MCP server is now active in all your projects.
Uninstall
pip uninstall project-brain-mcp
claude mcp remove project-brain --scope userMemory location
Memory is stored at ~/.project-brain/memory.json — shared across all projects, never committed to any repo.
To use a custom path:
export PROJECT_BRAIN_MEMORY_PATH=/path/to/memory.jsonTools
Tool | When to call |
| Session start — returns slim index |
| When index shows relevant entries — returns full content |
| Before any architectural proposal |
| When a decision is confirmed |
| When an investigation question is answered |
| When a wrong approach is identified |
| To correct an existing entry |
| To remove an outdated entry |
| To track unresolved questions |
How validate_plan works
validate_plan("use sqlite for storage", current_project="my-app")
→ conflicts: [entries from "my-app" that match — must resolve]
→ references: [entries from other projects — consider as context]Same project matches are hard conflicts. Other project matches are soft references.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceA persistent memory layer for Claude Code that maintains project information, technology stack, tasks, decisions, and session history between coding sessions, eliminating the need to re-explain project context.Last updated9MIT
- AlicenseCqualityAmaintenanceStores and recalls Claude Code session content as persistent memory, auto-injects relevant prior decisions and lessons at session start, and exposes 33 MCP tools for memory, knowledge-graph navigation, and cognitive profiling — backed by 41 neuroscience papers and 97.8% R@10 on LongMemEval.Last updated40668MIT
- Alicense-qualityCmaintenancePersistent memory for Claude Code — hybrid search, knowledge graph, session lifecycle.Last updatedMIT
- Alicense-qualityDmaintenancePersistent memory and automatic git snapshots for Claude Code, capturing decisions, patterns, and architecture across sessions.Last updated5697MIT
Related MCP Connectors
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
Experience memory for coding agents: validated traps, fixes and dead-ends at decision time.
Hosted memory for AI agents that learns and forgets — one key across Claude, Cursor & ChatGPT.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pym2282/project-brain-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server