Amnesic

by SurajKGoyal

273 downloads
Not rated
GitHub

About

Persistent semantic memory for SQL databases (Postgres, MySQL, MSSQL, SQLite). Annotate once, remember forever.

Details

Author
SurajKGoyal
Downloads
273
Categories
Database, AI

- Persistent SQLite knowledge store per database
- Read‑only by design with two independent safety layers
- Supports PostgreSQL, MySQL/MariaDB, SQL Server, and SQLite
- Credentials never appear in tool responses
- Nine MCP tools for schema, query, and annotation management

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Amnesic
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install with pipx install amnesic and run amnesic init to set up connections. The server exposes nine MCP tools for listing connections, querying schemas, executing read‑only SELECT queries, annotating database semantics, and managing knowledge across connections.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "amnesic": {
            "amnesic": {
                "command": "uvx",
                "args": [
                    "--from",
                    "amnesic[all]",
                    "amnesic"
                ]
            }
        }
    }
}

McpServers

{
    "amnesic": {
        "command": "uvx",
        "args": [
            "--from",
            "amnesic[all]",
            "amnesic"
        ]
    }
}

amnesic

Persistent semantic memory for your SQL databases. The name is ironic — it remembers everything. Every session with an AI starts cold: you re-explain what tables exist, what a status value of 3 means, which foreign key connects orders to users. amnesic fixes this with a local SQLite knowledge store — one per database — that survives across sessions. Annotate an enum once; every future session sees those labels automatically.

🔒 Read-only by design

Safe to point at production. Two independent layers: static SQL analysis rejects any write/DDL statement before connecting, and every query runs inside a transaction that is immediately rolled back. Credentials never appear in tool responses.

Supported databases

PostgreSQL · MySQL / MariaDB · Microsoft SQL Server · SQLite

Tools

| Tool | Description | |------|-------------| | db_list_connections | List configured connections (no secrets) | | db_list_tables | All known tables with descriptions | | db_search | BM25 search over table/column knowledge | | db_get_schema | Column schema merged with saved annotations | | db_query | Execute a read-only SELECT | | db_annotate | Persist semantic annotations (enum meanings, FKs) | | db_sync_knowledge | Copy annotations between connections (staging → prod) | | db_discover_relationships | Discover all FK relationships from the live DB | | db_get_relationships | Navigate the FK graph for JOIN planning |

Install

```bash pipx install amnesic amnesic init # interactive setup wizard
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.