list_tables

// WHEN AI AGENTS USE THIS TOOL

AI agents call list_tables 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_TABLES

Even though list_tables 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_tables:
    rules:
      - action: allow

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

// DETAILS

Tool Name list_tables

Category Read

MCP Server Amazon Redshift MCP Server MCP Server

Risk Level Low

// MORE AMAZON REDSHIFT MCP SERVER TOOLS

Execute execute_query Read list_clusters Read list_columns Read list_databases Read list_schemas

// WHAT CAN GO WRONG

Agents calling read-class tools like list_tables 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_tables tool do? +

List all tables in a specified schema within a Redshift database. This tool queries the SVV_ALL_TABLES system view to discover all tables that the user has access to in the specified schema, including base tables, views, external tables, and shared tables. ## Usage Requirements - Ensure your AWS credentials are properly configured (via AWS_PROFILE or default credentials). - The cluster must be available and accessible. - Required IAM permissions: redshift-data:ExecuteStatement, redshift-data:DescribeStatement, redshift-data:GetStatementResult. - The user must have access to the database to query system views. ## Parameters - cluster_identifier: The unique identifier of the Redshift cluster to query. IMPORTANT: Use a valid cluster identifier from the list_clusters tool. - table_database_name: The database name to list tables for. IMPORTANT: Use a valid database name from the list_databases tool. - table_schema_name: The schema name to list tables for. IMPORTANT: Use a valid schema name from the list_schemas tool. ## Response Structure Returns a list of RedshiftTable objects with the following structure: - database_name: The name of the database where the table exists. - schema_name: The schema name for the table. - table_name: The name of the table. - table_acl: The permissions for the specified user or user group for the table. - table_type: The type of the table (views, base tables, external tables, shared tables). - remarks: Remarks about the table. ## Usage Tips 1. First use list_clusters to get valid cluster identifiers. 2. Then use list_databases to get valid database names for the cluster. 3. Then use list_schemas to get valid schema names for the database. 4. Ensure the cluster status is 'available' before querying tables. 5. Note table types to understand if they are base tables, views, external tables, or shared tables. ## Interpretation Best Practices 1. Focus on 'TABLE' table types for regular database tables. 2. 'VIEW' table types indicate database views. 3. 'EXTERNAL TABLE' types indicate connections to external data sources. 4. 'SHARED TABLE' types indicate tables from datashares. 5. Use table names for subsequent column discovery and query operations. 6. Consider table permissions (table_acl) for access planning.. 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_tables? +

Add a rule in your Intercept YAML policy under the tools section for list_tables. 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_tables? +

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

Can I rate-limit list_tables? +

Yes. Add a rate_limit block to the list_tables 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_tables completely? +

Set action: deny in the Intercept policy for list_tables. 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_tables? +

list_tables 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.