sqlite_get_catalogLABSCO SUMMARY
Useful data for an agent without opening a system to it.
The database is a file and the metadata file is where you say what the columns mean and which queries you would rather it ran - so context and guard rails arrive in the same place, and no external system is exposed to get them.
What it is
A server over a SQLite database file and an optional metadata file. The catalogue call returns every table and column in one response, enriched with the descriptions you wrote in the metadata, and canned queries defined there become tools of their own.
What you get
- The structure of every table and column in one call, rather than a schema hunt
- Table and column descriptions taken from a YAML or JSON metadata file, so the agent reads your notes alongside the schema
- Arbitrary SQL executed against the database
- Canned queries from that same metadata file exposed as separate tools, so the question you want asked a particular way is the one on offer
- The same database and metadata file readable by Datasette, so people can browse what the agent queries
Requirements
uv, and a SQLite file. The metadata file is optional, but it is where the descriptions and the canned queries live. A sample configuration and a Titanic dataset ship with the repository - open it in VS Code with Copilot agent mode to see the tools before pointing it at your own data.
Setup effort
One command — uvx mcp-sqlite
USE CASES
01
Letting an agent answer from your data without connecting it to anything
Point it at a SQLite file: there is no server to reach and no credential to hand over.
02
Getting a straight answer out of an unfamiliar table
Read the whole catalogue in one call, descriptions included, then write the query.
03
Steering the agent toward the query you would have written
Define it in the metadata file and it appears as its own tool, so the question gets asked your way rather than improvised.
04
Letting people browse the same data the agent sees
The database and metadata file work with Datasette unchanged, so a human view costs nothing extra.
2 tools
Listed in project docs. Your client may show a different list.
sqlite_executeBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
uvx on PATH
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"mcp-sqlite": {
"command": "uvx",
"args": [
"mcp-sqlite"
]
}
}
}uvx
TERMINAL
uvx mcp-sqlite
