Skip to main content
Glama
neoai-agent

rds-mcp

by neoai-agent
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

RDS MCP Server

A Model Context Protocol (MCP) server for monitoring and analyzing Amazon RDS(MySQL, PostgreSQL) instances information, metrics and slowquery logs.

Installation

Install directly from GitHub using pipx:

# Install
pipx install git+https://github.com/neoai-agent/rds-mcp.git

# Or run without installation
pipx run git+https://github.com/neoai-agent/rds-mcp.git

Related MCP server: MCP-PostgreSQL-Ops

Quick Start

Authentication Options

The server supports multiple AWS authentication methods:

Option 1: IAM Roles (Recommended for EC2/ECS)

When running on AWS infrastructure with IAM roles attached, you can omit AWS credentials:

rds-mcp --openai-api-key "YOUR_OPENAI_API_KEY" --region "YOUR_AWS_REGION"

Option 2: AWS Access Keys

For local development or when IAM roles are not available:

rds-mcp --access-key "YOUR_AWS_ACCESS_KEY" --secret-access-key "YOUR_AWS_SECRET_KEY" --region "YOUR_AWS_REGION" --openai-api-key "YOUR_OPENAI_API_KEY"

Option 3: Environment Variables

You can also set AWS credentials via environment variables:

rds-mcp --access-key "YOUR_AWS_ACCESS_KEY" --secret-access-key "YOUR_AWS_SECRET_KEY" --region "YOUR_AWS_REGION" --openai_api_key "YOUR_OPENAI_API_KEY"

Note: When using IAM roles, the server will automatically use the default AWS credential chain, which includes IAM roles, environment variables, and AWS credentials file.

Available Tools

The server provides the following tools for RDS instance management and monitoring:

  1. Get RDS instance details:

await get_db_info(
    database_name="your-db-instance",
    region="your-aws-region"
)

  1. Get database metrics:

await get_database_metrics(
    database_name="your-db-instance",
    time_range_minutes=30
)

  1. Get slow queries:

await get_database_queries(
    database_name="your-db-instance",
    time_range_minutes=30
)

  1. Get instance performance metrics:

await get_top_rds_load(
    database_name="your-db-instance",
    time_range_minutes=30
)

Development

For development setup:

git clone https://github.com/neoai-agent/rds-mcp.git
cd rds-mcp
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -e ".[dev]"

License

MIT License - See LICENSE file for details

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • AWS FinOps MCP Server

    am2308
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables natural language analysis of AWS cloud costs, waste audits, and budget insights across multiple profiles and regions.
    MIT

  • MCP-PostgreSQL-Ops

    CharlotteDejager60506
    F
    license
    Not graded
    quality
    A
    maintenance
    Enables AI assistants to perform read-only PostgreSQL DBA work across versions 12–18, including performance analysis, slow query identification, bloat detection, lock and deadlock monitoring, autovacuum and schema inspection, and replication/WAL checks via natural language. Works with regular user permissions on RDS/Aurora without requiring any extensions, while optionally leveraging pg_stat_statements and pg_stat_monitor for deeper query analytics.
    -

  • MCP-PostgreSQL-Ops

    xu18613
    F
    license
    Not graded
    quality
    A
    maintenance
    Enables natural-language PostgreSQL operations and monitoring across PG 12-18 without requiring extensions, covering performance analysis, slow-query identification, bloat detection, lock and connection monitoring, autovacuum inspection, replication/WAL status, and schema relationship discovery. All operations are read-only and production-safe, working with regular user permissions on RDS/Aurora as well as self-hosted instances.
    -