Retrieve security findings from AWS security services. This tool provides a consolidated interface to retrieve findings from various AWS security services, including GuardDuty, Security Hub, Inspector, IAM Access Analyzer, and Trusted Advisor. It first checks if the specified security service i...
Part of the AWS Well-Architected Security Assessment Tool MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call GetSecurityFindings to retrieve information from AWS Well-Architected Security Assessment Tool 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 GetSecurityFindings 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:
GetSecurityFindings:
rules:
- action: allowSee the full AWS Well-Architected Security Assessment Tool MCP Server policy for all 6 tools.
Agents calling read-class tools like GetSecurityFindings 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.
Retrieve security findings from AWS security services. This tool provides a consolidated interface to retrieve findings from various AWS security services, including GuardDuty, Security Hub, Inspector, IAM Access Analyzer, and Trusted Advisor. It first checks if the specified security service is enabled in the region (using data from a previous CheckSecurityServices call) and only retrieves findings if the service is enabled. ## Response format Returns a dictionary with: - service: The security service findings were retrieved from - enabled: Whether the service is enabled in the specified region - findings: List of findings from the service (if service is enabled) - summary: Summary statistics about the findings (if service is enabled) - message: Status message or error information ## AWS permissions required - Read permissions for the specified security service ## Note For optimal performance, run CheckSecurityServices with store_in_context=True before using this tool. Otherwise, it will need to check if the service is enabled first.. It is categorised as a Read tool in the AWS Well-Architected Security Assessment Tool 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 GetSecurityFindings. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS Well-Architected Security Assessment Tool MCP Server MCP server.
GetSecurityFindings 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 GetSecurityFindings 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 GetSecurityFindings. 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.
GetSecurityFindings is provided by the AWS Well-Architected Security Assessment Tool MCP Server MCP server (awslabs.well-architected-security-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.