list_clusters

// WHEN AI AGENTS USE THIS TOOL

AI agents call list_clusters to retrieve information from Amazon Redshift MCP Server without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

// WHY ENFORCE A POLICY ON LIST_CLUSTERS

Even though list_clusters only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

// RECOMMENDED POLICY

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

amazon-redshift-mcp-server.yaml

tools:
  list_clusters:
    rules:
      - action: allow

See the full Amazon Redshift MCP Server policy for all 6 tools.

// DETAILS

Tool Name list_clusters

Category Read

MCP Server Amazon Redshift MCP Server MCP Server

Risk Level Low

// MORE AMAZON REDSHIFT MCP SERVER TOOLS

Execute execute_query Read list_columns Read list_databases Read list_schemas Read list_tables

// WHAT CAN GO WRONG

Agents calling read-class tools like list_clusters have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER READ TOOLS ACROSS MCP SERVERS

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

Firecrawl Web Scraping Server firecrawl_check_crawl_status Firecrawl Web Scraping Server firecrawl_crawl Firecrawl Web Scraping Server firecrawl_deep_research Firecrawl Web Scraping Server firecrawl_extract Firecrawl Web Scraping Server firecrawl_map Firecrawl Web Scraping Server firecrawl_scrape

// RELATED READING

// FAQ

What does the list_clusters tool do? +

List all available Amazon Redshift clusters and serverless workgroups. This tool discovers and returns information about all Redshift clusters and serverless workgroups in your AWS account, including their current status, connection details, and configuration. ## Usage Requirements - Ensure your AWS credentials are properly configured (via AWS_PROFILE or default credentials). - Required IAM permissions: redshift:DescribeClusters, redshift-serverless:ListWorkgroups, redshift-serverless:GetWorkgroup. ## Response Structure Returns a list of RedshiftCluster objects with the following structure: - identifier: Unique identifier for the cluster/workgroup. - type: Type of cluster (provisioned or serverless). - status: Current status of the cluster. - database_name: Default database name. - endpoint: Connection endpoint information. - port: Connection port. - vpc_id: VPC ID where the cluster resides. - node_type: Node type (for provisioned clusters). - number_of_nodes: Number of nodes (for provisioned clusters). - creation_time: When the cluster was created. - master_username: Master username for the cluster. - publicly_accessible: Whether the cluster is publicly accessible. - encrypted: Whether the cluster is encrypted. - tags: Tags associated with the cluster. ## Usage Tips 1. Use this tool to discover available Redshift instances before attempting connections. 2. Note the cluster identifiers for use with other database tools. 3. Check the status field to ensure clusters are 'available' before querying. 4. Use the endpoint and port information for direct database connections if needed. 5. Consider the cluster type (provisioned vs serverless) when planning your queries. ## Interpretation Best Practices 1. Filter results by status to find only available clusters. 2. Use cluster identifiers as input for other Redshift tools. 3. Consider cluster configuration (node type, encryption) for performance planning. 4. Check tags for environment or team information to select appropriate clusters.. It is categorised as a Read tool in the Amazon Redshift MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_clusters? +

Add a rule in your Intercept YAML policy under the tools section for list_clusters. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Amazon Redshift MCP Server MCP server.

What risk level is list_clusters? +

list_clusters is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_clusters? +

Yes. Add a rate_limit block to the list_clusters rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block list_clusters completely? +

Set action: deny in the Intercept policy for list_clusters. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides list_clusters? +

list_clusters is provided by the Amazon Redshift MCP Server MCP server (awslabs.redshift-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.