SQLite

Local MCP server for SQLite databases — query, manage schema, tables, indexes, and transactions through 15 tools.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Sqlite Query: Execute a SELECT query on the SQLite database and return rows as a JSON array. Use this for reading data — supports any valid SELECT statement with optional parameter binding for safe qu
  • Sqlite Execute: Execute a write statement (INSERT, UPDATE, DELETE, CREATE, ALTER, DROP) on the SQLite database. Returns the number of rows changed and the last inserted row ID. Use parameter binding f
  • Sqlite Run Script: Execute multiple SQL statements in a single transaction. All statements succeed or all fail (atomic). Separate statements with semicolons. Use for migrations, seed data, or batch op

What data it sees

Do you need an account

No: the server works without sign-in

Local MCP server for SQLite databases — query, manage schema, tables, indexes, and transactions through 15 tools. Install locally via npx only — each user gets their own database.

Features:

  • Execute SQL queries and statements with parameter binding
  • Full schema management (tables, columns, indexes, foreign keys)
  • Database analysis (size, table stats, integrity check)
  • WAL mode enabled for better concurrency

Install (Claude Desktop / Cursor): npx -y @node2flow/sqlite-mcp

Tool categories:

  • Query (3): execute_query, execute_run, execute_many
  • Schema (4): list_tables, describe_table, list_indexes, list_foreign_keys
  • Table (3): create_table, alter_table, drop_table
  • Index (2): create_index, drop_index
  • Database (3): get_info, vacuum, integrity_check

Configuration:

  • SQLITE_DB_PATH (required) — Path to your local SQLite database file
  • SQLITE_TIMEOUT (optional) — Busy timeout in milliseconds (default: 5000)

Note: This is a local-only tool. Install via npx to use your own database files.

How to connect

How to connect SQLite to Claude

The server address to paste into Claude settings:

https://sqlite--node2flow.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect SQLite to ChatGPT

The server address to paste into ChatGPT settings:

https://sqlite--node2flow.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect SQLite to Cursor

The server address to paste into Cursor settings:

https://sqlite--node2flow.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (15)

Raw names from tools/list. Only developers need these.

sqlite_queryExecute a SELECT query on the SQLite database and return rows as a JSON array. Use this for reading data — supports any valid SELECT statement with optional parameter binding for safe queries.
sqlite_executeExecute a write statement (INSERT, UPDATE, DELETE, CREATE, ALTER, DROP) on the SQLite database. Returns the number of rows changed and the last inserted row ID. Use parameter binding for safe writes.
sqlite_run_scriptExecute multiple SQL statements in a single transaction. All statements succeed or all fail (atomic). Separate statements with semicolons. Use for migrations, seed data, or batch operations.
sqlite_list_tablesList all tables and views in the database with their row counts. Use this as the first step to explore an unfamiliar database. Returns table name, type (table or view), and row count.
sqlite_describe_tableGet the column schema of a table — column names, data types, NOT NULL constraints, default values, and primary key flags. Also returns the CREATE TABLE SQL statement.
sqlite_list_indexesList all indexes on a table — index name, uniqueness, origin (manual or auto-created), and whether it is a partial index.
sqlite_list_foreign_keysList foreign key constraints on a table — referenced table, local and remote columns, ON UPDATE and ON DELETE actions.
sqlite_create_tableCreate a new table with column definitions. Each column has a name, type, and optional constraints (PRIMARY KEY, NOT NULL, UNIQUE, DEFAULT). Use ifNotExists to skip if the table already exists.
sqlite_alter_tableAlter an existing table — add a new column, rename a column, or rename the table. SQLite does not support dropping columns via ALTER TABLE.
sqlite_drop_tableDrop (delete) a table and all its data permanently. This action is irreversible. Use ifExists to avoid errors if the table does not exist.
sqlite_create_indexCreate an index on one or more columns to speed up queries. Optionally create a UNIQUE index to enforce uniqueness. Index name is auto-generated if not provided.
sqlite_drop_indexDrop (delete) an index by name. Does not affect the table data, only removes the index. Use ifExists to avoid errors if the index does not exist.
sqlite_get_infoGet database metadata — file path, file size, table count, page count, page size, journal mode, WAL status, encoding, and SQLite version. Use this to understand the database state.
sqlite_vacuumOptimize and compact the database file by rebuilding it. Reclaims space from deleted rows and defragments the file. Returns file size before and after. May take time on large databases.
sqlite_integrity_checkRun PRAGMA integrity_check to verify the database is not corrupted. Returns "ok" if the database is healthy, or a list of issues found. Use after crashes or suspicious behavior.