MCP server · Developer tools
Mneme Decision MCP server
by MnemeHQ
Lets your AI propose and look up your team's architecture decisions, while humans keep the final say.

Mneme is a helper that keeps your team's engineering decisions in one place and makes them available to AI coding tools. It is handy if you use an AI assistant to write or change code and you want it to follow the rules your team already agreed on. The Decision MCP server is the part that lets your AI ask about those decisions and suggest new ones.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another tool. This one connects your AI to Mneme, a place where your team's architecture decisions live. Once it is connected, your AI can look up decisions and suggest new ones for a person to review.
What this MCP server does
You ask your AI something about your project's rules, like which decisions apply to a certain folder. Your AI uses this helper to search Mneme's decision list. Mneme sends back the matching decisions and where they came from. If your AI wants to suggest a new decision, it can send a proposal, but that proposal is not official until a person accepts it. Everything stays on your computer, and no one can change the rules through the AI.
Click to zoomWhat you can do with it
- Look up which architecture decisions apply to a file or folder
- Search your team's recorded decisions by keyword
- Read the full text of a single decision
- Trace where a decision came from and what it replaced
- Suggest a new decision for a human to review
- Send several suggestions at once
- Check the current state of a decision proposal
Try asking your AI
- “Which architecture decisions apply to the config folder?”
- “Search our decisions for anything about JSON versus YAML”
- “Show me the full text of the decision called config-format”
- “Propose a new decision: we should use Postgres for all new services”
What it gives back to you
You get back a list of matching decisions with short summaries and their IDs. If you ask about one decision, you get its full text and where it came from. If you ask about a folder, you get the decisions that apply there. Proposals show up as suggestions waiting for a person to accept or reject.
Before you start
What you need
- Python 3.11 or newer installed on your computer
- The mneme-hq package installed with the MCP extra
- An MCP-capable AI client, like Claude Code or another tool that supports MCP
Good to know
The AI can only suggest new decisions, not approve them, so a person still has to accept or reject every proposal.
Install it with your AI
Add Mneme Decision MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Mneme Decision MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Software teams and developers who use AI coding assistants and want them to follow the team's architecture rules.





