Skip to main content
Glama
Raja SQL MCP

Raja SQL MCP

by Raja-genai

Raja SQL MCP

PyPI Python License

An MCP (Model Context Protocol) server for interacting with SQLite databases. This server provides tools to inspect database schemas, execute SQL queries, and perform CRUD operations, making it easy to integrate databases with AI agents and LLM-powered applications.


Features

✅ Execute SQL queries

✅ List all tables in the database

✅ Inspect table schemas

✅ Execute SELECT queries

✅ Insert data dynamically

✅ Update existing records

✅ Delete records safely

✅ SQLite-based (no external database server required)


Related MCP server: mcp-sqlite

Installation

pip install raja-sql-mcp

Running the Server

sql-mcp

Or during development:

uv run python -m src.sql_mcp.main

MCP Inspector Configuration

Transport

STDIO

Command

uv

Arguments

run python -m src.sql_mcp.main

Working Directory

/path/to/SQL_MCP

Available Tools

list_tables()

Returns all tables in the database.

Example:

list_tables()

describe_table(table_name)

Returns the schema of the specified table.

Example:

describe_table("users")

execute_sql(query)

Executes SQL queries such as:

  • CREATE TABLE

  • INSERT

  • UPDATE

  • DELETE

  • DROP TABLE

  • ALTER TABLE

Example:

execute_sql("""
CREATE TABLE users(
    id INTEGER PRIMARY KEY,
    name TEXT,
    age INTEGER
)
""")

execute_select(query)

Executes SELECT queries and returns rows.

Example:

execute_select(
    "SELECT * FROM users"
)

insert_data(table_name, data)

Insert records dynamically.

Example:

insert_data(
    "users",
    {
        "name": "Raja",
        "age": 21
    }
)

update_data(table_name, data, condition)

Update existing records.

Example:

update_data(
    "users",
    {
        "age": 22
    },
    "id = 1"
)

delete_data(table_name, condition)

Delete records matching a condition.

Example:

delete_data(
    "users",
    "id = 1"
)

Example Workflow

Create a table:

execute_sql("""
CREATE TABLE users(
    id INTEGER PRIMARY KEY,
    name TEXT,
    age INTEGER
)
""")

Insert data:

insert_data(
    "users",
    {
        "name": "Raja",
        "age": 20
    }
)

Query data:

execute_select(
    "SELECT * FROM users"
)

Update data:

update_data(
    "users",
    {
        "age": 21
    },
    "id = 1"
)

Delete data:

delete_data(
    "users",
    "id = 1"
)

Project Structure

SQL_MCP/
│
├── src/
│   └── sql_mcp/
│       ├── __init__.py
│       ├── database.py
│       ├── tools.py
│       └── main.py
│
├── README.md
├── LICENSE
├── pyproject.toml
└── uv.lock

Use Cases

  • AI Database Agents

  • Cursor-like Coding Assistants

  • LLM-powered CRUD Applications

  • Database Automation

  • Schema Inspection Tools

  • SQL Learning and Experimentation


License

MIT License © 2026 Anna Vamsi Krishna Raja

Available Tools

7 tools
delete_dataC

Delete Data from your table

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

describe_tableC

This function allows you to get schema of given table name

Inputs: table_name (required).

execute_selectC

Execute SELECT Queries and returns rows

Inputs: query (required).

execute_sqlC

This function helps to execute an sql query

Inputs: query (required).

insert_dataD

Insert Data into the table

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

list_tablesA

Get all the tables in your Database

Inputs: no named parameters.

update_dataD

Update data in the Table

Inputs: data (required), condition (required), table_name (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    C2.6/5.0

    Scored across 7 tools

    Disambiguation3/5

    Tools are mostly distinct, but execute_select and execute_sql have overlapping functionality since both can run SELECT queries, potentially confusing an agent.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern (e.g., delete_data, describe_table, execute_sql), with no mixing of conventions.

    Tool Count5/5

    7 tools is a well-scoped set for a SQL database server, covering essential operations without being excessive or insufficient.

    Completeness4/5

    Covers core CRUD and schema inspection, but lacks dedicated tools for table creation or alteration, though execute_sql can handle them.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A lightweight MCP server that provides read-only access to SQLite databases, allowing users to execute SELECT queries, list tables, and describe table schemas.
      1
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      MCP server that provides SQLite database operations. Allows AI assistants to query, modify and manage SQLite databases through the Model Context Protocol.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server for working with encrypted SQLite databases (SQLCipher), enabling database exploration, SQL queries, and CRUD operations through natural language.
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server providing SQLite database access for AI agents, enabling SQL execution, schema inspection, CRUD operations, and data export.
      MIT