Low Risk

call_api

call_api

How to control call_api ↓

What call_api does on AWS Infrastructure as Code MCP Server

AI agents call call_api as a supporting operation in AWS Infrastructure as Code MCP Server workflows.

Low Risk

Why call_api needs a policy

The description is completely empty, providing no information about what this tool does. The name 'call_api' is generic and could span any category from Read to Financial. Given the server context (AWS IaC, CloudFormation), it could execute AWS API calls with potentially significant blast radius, but without evidence I cannot confidently assign a more specific category.

From the tool's definition Tool name is 'call_api' with an empty description. No information about what API is called or what side effects may occur.

Documented attack patterns abuse exactly the kind of access call_api gives an agent:

How to control call_api

PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Infrastructure as Code MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for call_api:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "call_api": {
      "limits": [
        {
          "counter": "call_api_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

call_api gets a rate cap, and everything else on the server is denied unless you say otherwise.

  1. Create a free account and register AWS Infrastructure as Code MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
SET A RULE FOR THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about call_api

What does the call_api tool do? +

call_api. It is categorised as a Other tool in the AWS Infrastructure as Code MCP Server MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on call_api? +

Register the AWS Infrastructure as Code MCP Server MCP server in PolicyLayer and add a rule for call_api: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches AWS Infrastructure as Code MCP Server. Nothing to install.

What risk level is call_api? +

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

Can I rate-limit call_api? +

Yes. Add a rate_limit block to the call_api rule in your PolicyLayer 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 call_api completely? +

Set action: deny in the PolicyLayer policy for call_api. 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 call_api? +

call_api is provided by the AWS Infrastructure as Code MCP Server MCP server (awslabs.aws-iac-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AWS Infrastructure as Code MCP Server tool call.

Start from AWS Infrastructure as Code MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

805 AWS Infrastructure as Code MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.