Indexes the coding-agent sessions already sitting on your disk — months of history from before you installed it — and serves them back over MCP. 3.5 GB searched in ~1.5 ms, no LLM, no embeddings.
SQLite
Summary
Query, modify, and analyse a local SQLite database file directly from an AI client.
Features
- Query and modify a local SQLite database
- Schema inspection and table creation
- Built-in business-intelligence prompt for analysis
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
The reference SQLite MCP server gives an assistant full access to a local database file — read, write, and schema operations — with no server process to run.
What it exposes
- Read and write queries against the database, including creating tables and inserting rows
- Schema inspection — list tables, describe columns, and understand relationships
- An analysis prompt that guides the assistant through exploring a dataset and reporting findings, which is a genuinely useful starting point for ad-hoc analysis
Where it fits
SQLite is the natural format for anything small enough to be a file: exported data, local application state, scratch analysis, or a quick store an agent builds for itself. This server makes all of that directly addressable.
Because it allows writes, point it at a copy rather than the live database backing an application — the same advice as for any tool that will happily run DROP TABLE.
Installed with uvx mcp-server-sqlite --db-path path/to/file.db. Part of the MCP reference server collection.
Related MCP Servers
Weaviate's MCP server, built into the database itself — hybrid search, schema inspection, tenant listing and batch upserts at /v1/mcp, scoped by RBAC.
Google's open-source MCP server for enterprise databases — one binary that fronts AlloyDB, BigQuery, Spanner, Postgres, MySQL, Oracle, MongoDB, Snowflake and more.
A universal database MCP server — one integration for PostgreSQL, MySQL, SQL Server, SQLite, and MariaDB.
