@vinodismyname
基本信息
🤖 Enable AI assistants (Claude, Cursor) to monitor, diagnose, and query Amazon Redshift using this MCP server and the AWS Data API.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"redshift-utils-mcp": {
"command": "uv",
"args": [
"pip",
"install",
"redshift-utils-mcp"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Redshift Utils MCP Server is a Model Context Protocol server that bridges AI assistants (such as those in Claude, Cursor, or custom applications) with Amazon Redshift databases. It provides secure, standardized data access and interaction, allowing users to query data, understand database structure, and perform monitoring/diagnostic operations using natural language or AI-driven prompts. It is intended for developers, data analysts, and teams integrating LLM capabilities with Redshift.
Install via pip install redshift-utils-mcp or uv pip install redshift-utils-mcp. Set required environment variables (REDSHIFT_CLUSTER_ID, REDSHIFT_DATABASE, REDSHIFT_SECRET_ARN, AWS_REGION) then run redshift-utils-mcp or uvx redshift-utils-mcp. Configure the server in your MCP client (e.g., Claude Desktop, Claude Code CLI, Cursor IDE) by providing the command and environment variables.
Python 3.10+, `uv` or `pip`, an AWS account with Redshift Data API and Secrets Manager permissions, a Redshift cluster, and database credentials stored in AWS Secrets Manager. The Redshift user needs CONNECT and SELECT privileges on target tables and system views.
Set environment variables: `REDSHIFT_CLUSTER_ID`, `REDSHIFT_DATABASE`, `REDSHIFT_SECRET_ARN`, and `AWS_REGION`. Optionally set `AWS_PROFILE`. These can be defined in a shell, `.env` file, or directly in your MCP client configuration.
It uses Boto3 with the AWS credentials provided via environment variables, AWS profile, or IAM role. The server calls the Redshift Data API and accesses the specified Secrets Manager secret to retrieve database credentials. AWS credentials must have `redshift-data:*` and `secretsmanager:GetSecretValue` permissions.
The server uses the `stdio` transport, as shown in the Cursor IDE connection example. MCP clients connect via standard I/O to the server process.
No. Query execution is read-only (SELECT queries only). The server uses parameterized queries via the Redshift Data API to mitigate SQL injection risks. Other tools (inspect, diagnose, monitor) are also read-only.
Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.
Agent-Native Terminal
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
Most MCP servers hand your agent documentation. This one hands it a renderer. Write a single React Native codebase that ships native AR to phones and VR to headsets, then let your agent validate every prop, check each pl
评论