Skip to main content
Glama
Sign In
Redshift MCP Server

Redshift MCP Server

by DeepaRajareddy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Redshift MCP Server

A Model Context Protocol (MCP) server that enables AI agents to interact with Amazon Redshift using natural language.

Features

  • SQL Tools: Execute queries, list tables, describe schemas, get sample data.

  • Resources: Connection status, table list.

  • Sample Data: Pre-configured users, products, and orders tables.

  • Architecture: See DESIGN.md for system diagrams.

Related MCP server: Redshift MCP Server

🚀 Quick Start

For detailed instructions on Windows, macOS, and Linux, please refer to the SETUP.md guide.

Basic Steps (Local Testing):

  1. Start Postgres: docker run -d -p 5432:5432 --name postgres -e POSTGRES_PASSWORD=password postgres

  2. Install Deps: pip install mcp redshift-connector pandas python-dotenv psycopg2-binary sqlalchemy

  3. Seed Data: python seed_redshift.py

  4. Test: python test_redshift_local.py

🔧 MCP Client Configuration

Add this to your MCP client configuration (e.g., Antigravity, Claude Code, or VS Code).

"redshift-mcp": {
  "command": "py",
  "args": ["redshift_mcp_server.py"],
  "cwd": "c:/Users/deepa/OneDrive/Desktop/workspace/redis connection",
  "env": {
    "REDSHIFT_HOST": "localhost",
    "REDSHIFT_PORT": "5432",
    "REDSHIFT_DATABASE": "postgres",
    "REDSHIFT_USER": "postgres",
    "REDSHIFT_PASSWORD": "password"
  }
}

☁️ AWS Deployment

See AWS_DEPLOYMENT.md for deployment options.

Available Tools

5 tools
redshift_connection_statusB
Check the Redshift connection status.

Returns:
    Connection status information

Inputs: no named parameters. Returns: result

redshift_describe_tableB
Get the column definitions for a table.

Args:
    table_name: Name of the table
    schema: Schema name (default: "public")

Returns:
    JSON description of columns

Inputs: table_name (required), schema. Returns: result

redshift_get_sample_dataC
Get sample rows from a table.

Args:
    table_name: Name of the table
    limit: Number of rows to return (default: 5)
    schema: Schema name (default: "public")

Returns:
    JSON sample data

Inputs: table_name (required), limit, schema. Returns: result

redshift_list_tablesC
List all tables in a specific schema.

Args:
    schema: The schema name (default: "public")

Returns:
    JSON list of table names

Inputs: schema. Returns: result

redshift_queryC
Execute a SQL query on Redshift and return results as JSON.

Args:
    sql: The SQL query to execute

Returns:
    JSON string of the query results or error message

Inputs: sql (required). Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    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

    TDQS

    B3.4/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: connection status check, table description, data sampling, table listing, and query execution. The descriptions reinforce these distinct roles, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All tools follow a consistent 'redshift_' prefix with descriptive snake_case names (e.g., redshift_describe_table, redshift_query). This predictable pattern enhances readability and reduces cognitive load for users or agents.

    Tool Count4/5

    With 5 tools, the server is well-scoped for basic Redshift database interactions, covering essential operations like connection, metadata, and querying. It could be slightly expanded to include more advanced features (e.g., data modification), but the current count is reasonable for its purpose.

    Completeness3/5

    The toolset covers core read-only operations (status, metadata, querying) but lacks data manipulation tools (e.g., insert, update, delete) and schema management (e.g., create table). This creates gaps for agents needing full CRUD capabilities, though basic exploration and querying are well-supported.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Redshift MCP Server

      ConectcarData
      F
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs and AI agents to securely query and interact with Amazon Redshift databases with configurable access modes (readonly, readwrite, admin) for safe data exploration and management.
      -

    • Combined MCP Server

      manish6007
      A
      license
      A
      quality
      D
      maintenance
      Integrates Redshift database query capabilities with vector-based knowledgebase tools for semantic search and RAG applications. It enables users to execute SQL queries, explore database schemas, and perform hybrid semantic searches on markdown files stored in S3.
      7
      MIT

    • snowflake-mcp

      faressoft
      A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to execute SQL queries and explore Snowflake databases using natural language, with schema discovery, table inspection, and readonly mode.
      11
      571 npm
      MIT