Skip to main content
Glama

SkySQL MCP Server

Trust Score

This package contains everything needed to set up the SkySQL/MariaDB Cloud MCP (Model Context Protocol) server, which provides a powerful interface for managing SkySQL MariaDB database instances and interacting with AI Agents.

Features

  • Launch and manage serverless MariaDB database instances

  • Interact with AI-powered database agents

  • Execute SQL queries directly on SkySQL (MySQL/MariaDB) instances

  • Manage database credentials and IP allowlists

  • List and monitor database services

Related MCP server: MySQL MCP Server Pro

Installation

Prerequisites

  • Python 3.10 or higher

  • A SkySQL/MariaDB Cloud API key

Option 1: Run locally

Installation steps

  1. Clone the repository:

    git clone git@github.com:skysqlinc/skysql-mcp.git
    cd skysql-mcp
  2. Run the installation script:

    chmod +x install.sh
    ./install.sh
  3. Create a .env file in the root directory of the cloned git repository with your SkySQL API key. Obtain API key by signing up for free on SkySQL.

    SKYSQL_API_KEY=<your_skysql_api_key_here>
  4. Start the MCP server (HTTP mode):

    chmod +x launch.sh
    ./launch.sh

    The server will start on http://localhost:8000/mcp by default.

  5. Configure your IDE:

Cursor

Add the following to your Cursor MCP config (~/.cursor/mcp.json or .cursor/mcp.json in your project):

{
  "mcpServers": {
    "skysql-mcp-server": {
      "url": "http://localhost:8000/mcp",
      "headers": {
        "X-API-Key": "<your-skysql-api-key>"
      }
    }
  }
}

The X-API-Key header is sent with each request, allowing per-user API keys when the server is hosted remotely.

Windsurf

Add the following to your Windsurf MCP config (~/.codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "skysql-mcp-server": {
      "serverUrl": "http://localhost:8000/mcp"
    }
  }
}

Note: Windsurf uses serverUrl (not url) and cannot send request headers. Start the server in single-tenant mode so it falls back to the API key in your environment:

SKYSQL_SINGLE_TENANT=true ./launch.sh

With SKYSQL_API_KEY set in .env (step 3). Without SKYSQL_SINGLE_TENANT, the server requires every HTTP caller to supply its own X-API-Key header and will reject requests that don't — deliberately, so a shared deployment can never serve requests using the operator's key.

Claude

Add the server as a custom connector (Settings > Connectors > Add custom connector), then supply your API key under Request headers:

Field

Value

URL

your deployed server URL, ending in /mcp

Header name

x-api-key

Header value

your SkySQL API key, with no prefix

Required

yes

Generate the key at app.skysql.com/user-profile/api-keys. Enter it exactly as-is — Claude sends the value verbatim and does not add a scheme or prefix.

Claude requires a publicly reachable HTTPS URL, so http://localhost:8000/mcp will not work here; deploy the server first. Request header authentication is currently in beta and may need to be enabled for your organization.

  1. (Optional) Test the server interactively with MCP CLI:

    npx @wong2/mcp-cli uv run python src/mcp-server/server.py

Available Tools

8 tools
ask_agentB

Ask a question to a specific DB agent

Inputs: agent_id (required), question (required). Returns: result

delete_dbC

Delete a DB instance from SkySQL

Inputs: service_id (required). Returns: result

execute_sqlC

Execute SQL query on a SkySQL database instance and return the results

Inputs: sql_query (required), service_id (required). Returns: result

get_db_credentialsB

Get the credentials for a SkySQL database instance

Inputs: service_id (required). Returns: result

launch_serverless_dbC

Launch a new Serverless DB instance in SkySQL

Inputs: name (required), region, provider. Returns: result

list_agentsA

List all available SkySQL DB agents with their capabilities

Inputs: no named parameters. Returns: result

list_servicesA

List all available SkySQL database services

Inputs: no named parameters. Returns: result

update_ip_allowlistC

Update the IP allowlist for a SkySQL database instance with the current IP

Inputs: service_id (required). Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 8 tools

    Disambiguation4/5

    Tools are mostly distinct, covering agent interactions and database lifecycle management. The only slight overlap is between list_agents and list_services, but the entity types (agents vs services) are clearly different, reducing selection risk.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (list, launch, delete, ask, get, update, execute), with no mixed conventions or unclear verbs. The naming is predictable and readable.

    Tool Count5/5

    With 8 tools, the server is well-scoped for its purpose, balancing database operations with agent interaction without redundancy or unnecessary bloat.

    Completeness4/5

    Core database lifecycle is covered (launch, delete, list, credentials, SQL execution), plus agent interaction. Minor gaps exist, such as lack of explicit service status checks or credential rotation, but these are not critical for the main workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to interact with MariaDB databases through standard SQL operations and advanced vector/embedding-based search. Supports database management, schema inspection, and semantic document storage and retrieval with multiple embedding providers.
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Provides comprehensive MySQL database operations including CRUD, performance optimization, health analysis, and anomaly detection. Supports multiple connection modes, OAuth2.0 authentication, and role-based permissions for database management through natural language.
      9
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables management of CCX database clusters through AI assistants, supporting operations such as datastore creation, scaling, and performance monitoring. It provides a comprehensive toolset for handling backups, database users, and firewall rules across various database engines including PostgreSQL, MySQL, and Redis.
      1
      Apache 2.0
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables comprehensive monitoring and analysis of Oracle Cloud Infrastructure database fleets through natural language interfaces. It supports performance troubleshooting, capacity planning, and automated DBA workflows across multi-tenant environments using specialized tools and playbooks.
      1
      -