How does Amnesic ensure queries are safe for production?
It uses 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.
@SurajKGoyal
基本信息
Persistent semantic memory for SQL databases (Postgres, MySQL, MSSQL, SQLite). Annotate once, remember forever.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"amnesic": {
"command": "uvx",
"args": [
"--from",
"amnesic[all]",
"amnesic"
]
}
}
}List configured connections (no secrets)
All known tables with descriptions
BM25 search over table/column knowledge
Column schema merged with saved annotations
Execute a read-only SELECT
Persist semantic annotations (enum meanings, FKs)
Copy annotations between connections (staging → prod)
Discover all FK relationships from the live DB
Navigate the FK graph for JOIN planning
Amnesic is an MCP server that provides persistent semantic memory for SQL databases, allowing AI sessions to retain knowledge about table schemas, enum meanings, and foreign key relationships across sessions. It is intended for developers and data professionals who want to avoid re-explaining database context when interacting with AI tools.
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.
It uses 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.
PostgreSQL, MySQL/MariaDB, Microsoft SQL Server, and SQLite.
No, credentials are never exposed in tool responses.
Yes, the `db_sync_knowledge` tool copies annotations between connections (e.g., from staging to production).
In a local SQLite knowledge store, one per database, that persists across sessions.

Access millions of official legal and regulatory source documents from 155+ jurisdictions via MCP. Lawstronaut supports AI agents with structured legal research, legal data, laws, regulations, cases, guidance, official s
Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.
A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.
Connect ClickHouse to your AI assistants.
An official Qdrant Model Context Protocol (MCP) server implementation
评论