// MCP TOOL REFERENCE

explain

Accepts raw HTML/template content (content)

Part of the AWS Cloud Control API (CCAPI) MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

awslabs.ccapi-mcp-server Destructive

// WHEN AI AGENTS USE THIS TOOL

AI agents may call explain to permanently remove or destroy resources in AWS Cloud Control API (CCAPI) MCP Server. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.

// WHY ENFORCE A POLICY ON EXPLAIN

Without a policy, an AI agent could call explain in a loop, permanently destroying resources in AWS Cloud Control API (CCAPI) MCP Server. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.

// RECOMMENDED POLICY

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

aws-cloud-control-api-ccapi-mcp-server.yaml

tools:
  explain:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full AWS Cloud Control API (CCAPI) MCP Server policy for all 14 tools.

// DETAILS

Tool Name explain

Category Destructive

MCP Server AWS Cloud Control API (CCAPI) MCP Server MCP Server

Risk Level Critical

// MORE AWS CLOUD CONTROL API (CCAPI) MCP SERVER TOOLS

Destructive delete_resource Execute run_checkov Write create_resource Write create_template Write generate_infrastructure_code Write update_resource Read check_environment_variables Read get_aws_account_info

View all 14 tools →

// WHAT CAN GO WRONG

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

Browse the full MCP Attack Database →

// OTHER DESTRUCTIVE TOOLS ACROSS MCP SERVERS

Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.

AbraFlexi contact_delete AbraFlexi evidence_delete AbraFlexi invoice_issued_delete AbraFlexi product_delete ACR — Agent Composition Records acknowledge_signal AdButler campaign_bulk_delete_catalog_ad_items

// IN CONTEXT OF CRITICAL RISK

explain is one of the critical-risk operations in AWS Cloud Control API (CCAPI) MCP Server. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the explain tool do? +

MANDATORY: Explain any data in clear, human-readable format. For infrastructure operations (create/update/delete): - CONSUMES generated_code_token and returns explained_token - You MUST immediately display the returned explanation to user - You MUST use the returned explained_token for create/update/delete operations For general data explanation: - Pass any data in 'content' parameter - Provides comprehensive explanation of the data structure CRITICAL: You MUST immediately display the full explanation content to the user after calling this tool. The response contains an 'explanation' field that you MUST show to the user - this is MANDATORY. Never proceed with create/update/delete operations without first showing the user what will happen. Returns: explanation: Comprehensive explanation you MUST display to user explained_token: New token for infrastructure operations (if applicable). It is categorised as a Destructive tool in the AWS Cloud Control API (CCAPI) MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on explain? +

Add a rule in your Intercept YAML policy under the tools section for explain. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS Cloud Control API (CCAPI) MCP Server MCP server.

What risk level is explain? +

explain is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit explain? +

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

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

explain is provided by the AWS Cloud Control API (CCAPI) MCP Server MCP server (awslabs.ccapi-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

explain

Let agents act without letting them run wild.