Low Risk

describe-service-updates

Returns details of the service updates. Parameters: service_update_name (Optional[str]): The unique ID of the service update to describe. service_update_status (Optional[List[str]]): List of status values to filter by. Valid values: available | cancelled | expired | complete ...

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

AI agents call describe-service-updates to retrieve information from AWS ElastiCache 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 describe-service-updates 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-elasticache-mcp-server.yaml
tools:
  describe-service-updates:
    rules:
      - action: allow

See the full AWS ElastiCache MCP Server policy for all 39 tools.

Tool Name describe-service-updates
Category Read
Risk Level Low

View all 39 tools →

Agents calling read-class tools like describe-service-updates 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 describe-service-updates tool do? +

Returns details of the service updates. Parameters: service_update_name (Optional[str]): The unique ID of the service update to describe. service_update_status (Optional[List[str]]): List of status values to filter by. Valid values: available | cancelled | expired | complete starting_token (Optional[str]): An optional token returned from a previous request. Use this token for pagination of results from this operation. page_size (Optional[int]): The maximum number of records to include in each page of results. max_items (Optional[int]): The maximum number of records to include in the response. If more records exist than the specified MaxItems value, a marker is included in the response so that the remaining results can be retrieved. Returns: Dict containing information about the service updates, including: - ServiceUpdates: List of service updates - NextToken: Token for next set of results. It is categorised as a Read tool in the AWS ElastiCache MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on describe-service-updates? +

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

What risk level is describe-service-updates? +

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

Can I rate-limit describe-service-updates? +

Yes. Add a rate_limit block to the describe-service-updates 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 describe-service-updates completely? +

Set action: deny in the Intercept policy for describe-service-updates. 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 describe-service-updates? +

describe-service-updates is provided by the AWS ElastiCache MCP Server MCP server (awslabs.elasticache-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.