Skip to main content
Glama
Mcp Server Sqlite Fast

Mcp Server Sqlite Fast

by Dali5599

Mcp Server Sqlite Fast 🦈⭐

Stars License: MIT PRs Welcome TypeScript Model Context Protocol Engineered by Requin

High-performance Model Context Protocol (MCP) server providing secure read/write queries, schema introspection, and execution plan analysis for SQLite with zero external binary dependencies.


⚡ Highlights

  • Zero Native C++ Compilation Woes: Built on Node 24 native synchronous SQLite (node:sqlite), guaranteed instant startup without node-gyp errors.

  • Introspection & Schema Discovery: Auto-inspects tables, foreign keys, indexes, and column types.

  • Strict Read-Only Guardrails: Enforces safety constraints to prevent accidental database drops or mutations during agent autonomous exploration.

  • Explain Query Plan: Built-in EXPLAIN execution plan tool for database indexing recommendations.

  • Universal AI Agent Compatibility: Plug-and-play with Claude Code, Cursor, Windsurf, Zed, and any MCP-compliant client.


Related MCP server: sql-guard-mcp

🚀 Quickstart

1. Installation & Build

git clone https://github.com/Dali5599/mcp-server-sqlite-fast.git
cd mcp-server-sqlite-fast
npm install
npm run build

2. Configure with Claude Desktop or Claude Code

Add to your claude_desktop_config.json or mcp.json:

{
  "mcpServers": {
    "sqlite-fast": {
      "command": "node",
      "args": [
        "/path/to/mcp-server-sqlite-fast/dist/index.js"
      ]
    }
  }
}

🛠️ Available MCP Tools

Tool

Parameters

Description

list_tables

db_path

Lists all tables, views, and schemas in the SQLite database.

describe_table

db_path, table_name

Introspects table columns, primary keys, and foreign keys.

execute_query

db_path, query, params, read_only

Executes SQL queries with optional parameterized arguments.

explain_query

db_path, query

Analyzes execution plan to optimize indexing and query performance.


🧪 Testing

npm test

All 5 automated unit tests execute with sub-millisecond latency.


📜 License

MIT License - Developed with precision by Dali & Requin Autonomous AI.

Available Tools

4 tools
describe_tableB

Introspect table schema, column types, primary keys, and foreign keys.

Inputs: db_path (required), table_name (required).

execute_queryC

Execute a read-only or read/write SQL query with safety constraints.

Inputs: query (required), db_path (required), params, read_only.

explain_queryB

Get the SQLite EXPLAIN QUERY PLAN analysis to optimize indexing.

Inputs: query (required), db_path (required).

list_tablesB

List all tables, views, and row counts in a SQLite database.

Inputs: db_path (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 4 tools

    Disambiguation4/5

    Each tool has a distinct primary purpose: listing tables, describing schema, executing SQL, and explaining query plans. There is mild overlap because execute_query could run EXPLAIN statements, but the specialized explain_query makes the intent clear.

    Naming Consistency5/5

    All four tools follow a consistent snake_case verb_noun pattern: list_tables, describe_table, execute_query, explain_query. The convention is predictable throughout.

    Tool Count5/5

    Four tools are well-scoped for a focused SQLite query/analysis server. Each tool earns its place without redundant surface area.

    Completeness4/5

    The surface covers discovery, schema introspection, query execution, and query-plan optimization. Some database operations like index listing or explicit transaction management rely on execute_query, which is a minor gap rather than a blocker.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Lets AI agents query local SQLite database files read-only using Node's built-in sqlite module, providing tools for listing tables, describing schemas, and running SQL queries.
      3
      10 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to safely query and explore SQLite databases through read-only, guard-protected tools that block writes, sensitive table access, and runaway queries.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to safely explore and query databases across SQLite, PostgreSQL, MySQL, and MSSQL, with schema introspection, natural language queries, and data profiling.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to inspect database schemas and run strictly read-only SQL queries with guardrails against destructive statements, multi-statement chaining, and unbounded scans. Supports SQLite natively and PostgreSQL optionally.
      4
      37 PyPI
      MIT