# mnemonic MCP server

> Provides project-scoped memory for AI clients using markdown files and git-synced semantic search.

- Repository: https://github.com/danielmarbach/mnemonic
- Page: https://hostedmcp.org/servers/danielmarbach/mnemonic
- Transport: —
- Stars: 32
- License: Apache-2.0

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `VAULT_PATH` | no | no |  |

## Tools (40)

- `add_attachment`
- `consolidate`
- `detect_project`
- `discover_tags`
- `execute_migration`
- `forget`
- `get`
- `get_project_identity`
- `get_project_memory_policy`
- `list`
- `list_attachments`
- `list_migrations`
- `memory_graph`
- `move_memory`
- `project_memory_summary`
- `recall`
- `recent_memories`
- `remember`
- `relate`
- `remove_attachment`
- `set_attachment_branch`
- `set_attachment_enabled`
- `set_project_identity`
- `set_project_memory_policy`
- `sync`
- `unrelate`
- `update`
- `where_is_memory`
- `related-to`
- `explains`
- `example-of`
- `supersedes`
- `derives-from`
- `follows`
- `kind`
- `root`
- `include`
- `exclude`
- `branch`
- `writable`

## FAQ

### Does mnemonic require a database?

No, it uses plain markdown files and JSON files synced via git, requiring no database or always-on service.

### How does mnemonic handle embeddings?

Embeddings stay local and are gitignored, allowing for semantic retrieval without committing vector data.

### Can I use mnemonic with Docker?

Yes, you can use Docker Compose to run mnemonic with an Ollama container.
