Comprehensive Kafka ESM troubleshooting tool for both MSK and self-managed Kafka. This unified tool supports both Amazon MSK and self-managed Apache Kafka clusters. It can either diagnose timeout issues by analyzing when they occur, or provide targeted resolution steps for specific identified pr...
Part of the AWS Serverless MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call esm_kafka_troubleshoot to retrieve information from AWS Serverless 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 esm_kafka_troubleshoot 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.
tools:
esm_kafka_troubleshoot:
rules:
- action: allowSee the full AWS Serverless MCP Server policy for all 32 tools.
Agents calling read-class tools like esm_kafka_troubleshoot have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Comprehensive Kafka ESM troubleshooting tool for both MSK and self-managed Kafka. This unified tool supports both Amazon MSK and self-managed Apache Kafka clusters. It can either diagnose timeout issues by analyzing when they occur, or provide targeted resolution steps for specific identified problems. Args: ctx: The execution context kafka_type: Type of Kafka cluster (MSK, self-managed, or auto-detect) issue_type: 'diagnosis' for problem identification, or specific issue type for resolution Returns: Dict containing diagnostic indicators or resolution steps based on kafka_type and issue_type. It is categorised as a Read tool in the AWS Serverless MCP Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for esm_kafka_troubleshoot. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS Serverless MCP Server MCP server.
esm_kafka_troubleshoot is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the esm_kafka_troubleshoot 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.
Set action: deny in the Intercept policy for esm_kafka_troubleshoot. 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.
esm_kafka_troubleshoot is provided by the AWS Serverless MCP Server MCP server (awslabs.aws-serverless-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.