---
title: "SQLite MCP Server for ToolPiper · ModelPiper"
description: "Query SQLite databases and run business-intelligence prompts. Point this at a `.db` file and the model can run SQL against it, read and write. Six tools: `read_query` (SELECT), `write_query` (INSERT/UPDATE/DELETE), `crea"
canonical: "https://modelpiper.com/mcp-tools/sqlite"
---

# SQLite MCP Server for ToolPiper · ModelPiper

> Query SQLite databases and run business-intelligence prompts. Point this at a `.db` file and the model can run SQL against it, read and write. Six tools: `read_query` (SELECT), `write_query` (INSERT/UPDATE/DELETE), `crea

S

# SQLite MCP Server

✓ verified

Query SQLite databases and run business-intelligence prompts.

Install SQLite in ToolPiper

Don't have ToolPiper? We'll take you to the download.

[Open repository →](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/sqlite)

Publisher

[Anthropic Reference (archived)](https://github.com/modelcontextprotocol/servers-archived)

License

MIT

Transport

Local subprocess

Tools

4

## What this server does

Point this at a \`.db\` file and the model can run SQL against it, read and write. Six tools: \`read\_query\` (SELECT), \`write\_query\` (INSERT/UPDATE/DELETE), \`create\_table\` (DDL), \`list\_tables\`, \`describe-table\`, and \`append\_insight\`. The last one is unusual: it appends a string to a \`memo://insights\` resource that the host can re-read, so the model can build up a running narrative of what it has discovered as it works through the data. A built-in prompt called \`mcp-demo\` takes a business domain as its \`topic\` argument, generates a schema, populates sample data, and walks you through an analysis. It is a tutorial fixture, not a production workflow, but it is a fast way to see what the BI loop is supposed to feel like. Unlike the Postgres MCP server, which is read-only by construction, this one is read-write. \`write\_query\` and \`create\_table\` modify the database directly. There is no transaction isolation across tool calls. Each query commits when it returns. If you only want analytics, do not give the model the path to your production SQLite file. Best fit: an analytics scratch DB, a SQLite dump pulled from production for one-off questions, or learning what the model can do with the included BI prompt template. The reference is archived but the protocol surface is stable; queries that work today will work tomorrow.

## Tools included

-   read\_query
    
    Run a read-only SELECT query.
    
-   write\_query
    
    Run an INSERT / UPDATE / DELETE statement.
    
-   list\_tables
    
    List all tables in the database.
    
-   describe\_table
    
    Show the schema of a table.
    

The authoritative list comes from the server's tools/list at runtime. This catalog entry may lag the upstream until the next ToolPiper release.

## Install in ToolPiper

ToolPiper handles the JSON configuration. Click Install, fill in any required tokens, and the server is ready in your chat.

Install SQLite in ToolPiper

Don't have ToolPiper? We'll take you to the download.

## Install in another client

Install in another MCP client (Claude Desktop, Cursor, Continue, Cline)

Claude Desktop Cursor Continue Cline

Add this to ~/Library/Application Support/Claude/claude\_desktop\_config.json.

```
{
  "mcpServers": {
    "sqlite": {
      "command": "uvx",
      "args": [
        "mcp-server-sqlite",
        "--db-path",
        "${SQLITE_DB_PATH}"
      ]
    }
  }
}
```

Copy

## Example prompts

-   "List the tables in this database and describe each schema."
    
    Copy
-   "How many users signed up each day in March?"
    
    Copy
-   "Run the mcp-demo prompt with topic 'subscription churn'."
    
    Copy
-   "Add an insight: 'High-value customers churn 3x slower than median.'"
    
    Copy

## Security notes

This server is read-write by default. Anything the model can express in SQL it can execute, including \`DROP TABLE\`. Point it at a copy of your data, not the original, unless you trust the model's discipline. There is no SQL parser between the model and SQLite; the query goes straight through. The database file lives wherever \`--db-path\` points, so secrets in that file are visible to the assistant. For production analytics, prefer Postgres with a read-only role and the Postgres MCP server. The upstream reference is archived; no official replacement has shipped, though community forks exist.

## Related tools

-   [
    
    P
    
    ### Postgres
    
    ✓ verified
    
    Query Postgres databases with read-only SQL.
    
    DataLocal subprocess1 tool
    
    
    
    
    
    ](/mcp-tools/postgres)
-   [
    
    R
    
    ### Redis
    
    ✓ verified
    
    Interact with Redis key-value stores from the assistant.
    
    DataLocal subprocess4 tools
    
    
    
    
    
    ](/mcp-tools/redis)
-   [
    
    A
    
    ### AWS Knowledge Base
    
    ✓ verified
    
    Retrieve answers from an AWS Bedrock Knowledge Base.
    
    DataLocal subprocess1 tool
    
    
    
    
    
    ](/mcp-tools/aws-kb-retrieval)
-   [
    
    M
    
    ### MongoDB
    
    ✓ verified
    
    Query and manage MongoDB and Atlas clusters from the assistant.
    
    DataLocal subprocess5 tools
    
    
    
    
    
    ](/mcp-tools/mongodb)

[← Back to all MCP tools](/mcp-tools)