mnemodb — Claude Code MCP server: what it does, how to install
Keeps agent memory inside plain Markdown files in your repository, with Git history, trust levels, and lifecycle tracking.
claude mcp add --env MNEMO_STORE=<MNEMO_STORE> --transport stdio mnemodb -- npx -y @mnemodb/mcpWhat mnemodb does
MnemoDB structures persistent agent context as plain .mem.md files in the repository. Each entry uses a standard Markdown heading accompanied by inline metadata for source attribution, confidence, and supersession. You can inspect the files manually and review memory updates via standard git diff.
Under the hood, the server exposes eleven memory-focused tools, including memory_recall, memory_remember, and memory_compact. The internal trust model flags facts gathered from tool executions as untrusted, preventing external outputs from overwriting manual rules set by the engineer.
Running the package requires npx, and storage defaults to a local .memory/ directory created upon the first saved entry.
What it helps with
- store agent decisions in plain repository files that track cleanly in Git
- prevent tool outputs from overwriting instructions set by the developer
- retire stale context entries through auditable compaction
- share agent knowledge between Claude Code, Cursor, and other MCP clients
Example prompts for the agent
- Remember that our team prefers pnpm over npm for package management
- Recall project architectural decisions before drafting this service
- Run a compaction pass to archive expired context entries
How to install mnemodb
Platform CLI
claude mcp add --env MNEMO_STORE=<MNEMO_STORE> --transport stdio mnemodb -- npx -y @mnemodb/mcpReplace <…> with your own values
Platform CLI
codex mcp add mnemodb --env MNEMO_STORE=<MNEMO_STORE> -- npx -y @mnemodb/mcpReplace <…> with your own values
Config file
{
"mcpServers": {
"mnemodb": {
"command": "npx",
"args": [
"-y",
"@mnemodb/mcp"
],
"env": {
"MNEMO_STORE": "<MNEMO_STORE>"
}
}
}
}Replace <…> with your own values
Config file
{
"servers": {
"mnemodb": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mnemodb/mcp"
],
"env": {
"MNEMO_STORE": "<MNEMO_STORE>"
}
}
}
}Replace <…> with your own values
Platform CLI
gemini mcp add -e MNEMO_STORE=<MNEMO_STORE> mnemodb npx -y @mnemodb/mcpReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about mnemodb
How do I install mnemodb in Claude Code?
Run claude mcp add mnemodb -- npx -y @mnemodb/mcp in your terminal. If you need a custom store path, add --env MNEMO_STORE=<MNEMO_STORE>.
What does mnemodb do?
It manages persistent agent memory through structured Markdown files inside your repository. The server tracks provenance, manages record lifecycles, and lets you inspect memory changes with regular git commands.
How does the trust model handle external tool output?
Information saved from external tools is assigned a tool provenance tag and marked untrusted. These records cannot supersede or purge memories created directly by the user.
