Low Risk

ListECRRepositories

List ECR repositories with HealthOmics accessibility status. Lists all ECR repositories in the current region and checks each repository's policy to determine if HealthOmics has the required permissions to pull images. Args: ctx: MCP context for error reporting max_results: Maximum numb...

Part of the AWS HealthOmics MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call ListECRRepositories to retrieve information from AWS HealthOmics 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.

Even though ListECRRepositories 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.

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

aws-healthomics-mcp-server.yaml
tools:
  ListECRRepositories:
    rules:
      - action: allow

See the full AWS HealthOmics MCP Server policy for all 73 tools.

Tool Name ListECRRepositories
Category Read
Risk Level Low

View all 73 tools →

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

Browse the full MCP Attack Database →

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

What does the ListECRRepositories tool do? +

List ECR repositories with HealthOmics accessibility status. Lists all ECR repositories in the current region and checks each repository's policy to determine if HealthOmics has the required permissions to pull images. Args: ctx: MCP context for error reporting max_results: Maximum number of results to return (default: 100, max: 1000) next_token: Pagination token from a previous response filter_healthomics_accessible: If True, only return repositories that are accessible by HealthOmics aws_profile: Optional AWS profile name override aws_region: Optional AWS region override Returns: Dictionary containing: - repositories: List of ECR repositories with accessibility status - next_token: Pagination token if more results are available - total_count: Total number of repositories returned. It is categorised as a Read tool in the AWS HealthOmics MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ListECRRepositories? +

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

What risk level is ListECRRepositories? +

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

Can I rate-limit ListECRRepositories? +

Yes. Add a rate_limit block to the ListECRRepositories 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 ListECRRepositories completely? +

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

ListECRRepositories is provided by the AWS HealthOmics MCP Server MCP server (awslabs.aws-healthomics-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.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.