SQLite MCP Server
Not yet source-checkedReference MCP server for querying and analyzing SQLite databases through Claude and other MCP clients.
Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked How we rate
In short
A free, open-source MCP server for querying local SQLite databases via Claude. Archived in 2025, it serves as a reference implementation for developers.
Developers and analysts who want an LLM to explore a local SQLite database through Claude Desktop or VS Code, and MCP server authors looking for a small, readable reference implementation to fork.
Teams that need a maintained, hardened database connector, non-SQLite engines, multi-user access controls, or any production system where an archived upstream is a non-starter.
The SQLite MCP Server is a reference Model Context Protocol server originally maintained by the MCP core team that turns any local SQLite database into a first-class tool surface for Claude Desktop, VS Code and other MCP-compatible clients. It exposes a small, focused toolbelt (`read_query`, `write_query`, `create_table`, `list_tables`, `describe_table`) plus an `append_insight` tool and a `memo://insights` resource that accumulates business findings across a conversation, so the model can build up a running analysis memo instead of restating context each turn. A bundled `mcp-demo` prompt walks the model through a guided business-intelligence workflow against a topic you supply.
It is aimed at developers, analysts and prompt engineers who want to let an LLM explore a real relational dataset without hand-rolling a bespoke integration — think ad-hoc data exploration, prototyping agentic BI flows, teaching an LLM to write SQL against a schema it can introspect, or wiring a local SQLite cache into a larger agent stack. Deployment is deliberately trivial: `uv run mcp-server-sqlite --db-path ~/test.db`, a Docker image with a mounted volume, or the one-click VS Code install buttons in the README. Configuration snippets for Claude Desktop and VS Code are included.
Important caveat: the repository was archived on 29 May 2025 and moved to `servers-archived`, alongside other early reference servers that the MCP team retired in favour of community-maintained implementations. The code still works and remains under MIT license, but it will no longer receive fixes, security patches or feature work from the upstream maintainers, so treat it as a stable reference rather than a production dependency.
A tidy, honest reference server — the six-tool surface plus the insights-memo pattern is genuinely instructive, and it is still the shortest path from a .db file to a Claude conversation that can actually query it. Just treat the archived status seriously: fine for local exploration and as a template, not something I would pin a production agent to without forking.
— The AI Tool Bible editorial team
Pros
- ✅ Zero-config local database access for any MCP client — point it at a .db file and Claude can query, schema-introspect and write immediately.
- ✅ Clean, minimal tool surface (six tools) that maps cleanly to how an LLM actually reasons about a database.
- ✅ Novel `append_insight` + `memo://insights` pattern gives the model a persistent scratchpad for multi-turn analysis.
- ✅ MIT-licensed and open source, so it doubles as a canonical example for building your own MCP server.
- ✅ Multiple install paths — uv, Docker, VS Code one-click — cover most developer setups.
- ✅ No API keys, no cloud, no per-query cost; everything runs on your machine against a file you own.
Cons
- ⚠️ Repository was archived on 29 May 2025 — no more upstream fixes, security patches or new features.
- ⚠️ Exposes `write_query` and `create_table` to the model, so a careless prompt can mutate or drop data; there is no built-in read-only mode or row-level safety.
- ⚠️ SQLite-only — no Postgres, MySQL, DuckDB or cloud-warehouse support; you need a different MCP server for those.
- ⚠️ No authentication, quota or audit layer; intended for local single-user use, not shared/multi-tenant deployments.
- ⚠️ Insight-memo state lives in the running server process, so it does not survive restarts or multiple concurrent clients cleanly.
Facts
- Open source
- Yes (license: MIT)
- GitHub stars
- 305 (checked Oct 29, 2026)
- Last GitHub push
- May 28, 2025
- First commit
- May 2025
- Archived on GitHub
- Yes
Where this tool sits
Use cases
Frequently asked
- Is the SQLite MCP Server free to use?
- Yes, it is free and open source under the MIT license. There are no usage fees, and it runs locally against a SQLite file you control, making it cost-effective for development and prototyping.
- Is this server suitable for production environments?
- No. The repository was archived in May 2025 and will no longer receive fixes or security patches. It is intended as a stable reference implementation, not a maintained, hardened connector for production systems requiring multi-user access controls.
- Which clients and platforms does it integrate with?
- It integrates with Claude Desktop, VS Code, and other MCP-compatible clients. Deployment is simple via `uv run`, Docker, or one-click VS Code install buttons, with configuration snippets provided for both Claude Desktop and VS Code.
- What specific tools and features does it expose?
- It exposes tools like `read_query`, `write_query`, `create_table`, `list_tables`, and `describe_table`. It also includes an `append_insight` tool and a `memo://insights` resource to accumulate business findings across a conversation, supporting guided business-intelligence workflows.
- Who is this tool best suited for?
- It is best for developers, analysts, and prompt engineers who want an LLM to explore local SQLite databases. It is also useful for MCP server authors looking for a small, readable reference implementation to fork for custom integrations.