wrap_call · SelfHeal MCP: Risk & Policy

WHAT IT DOES

What wrap_call does on SelfHeal MCP

AI agents invoke wrap_call to trigger actions in SelfHeal MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why wrap_call needs a policy

While the tool itself is a wrapper/proxy mechanism, it ultimately executes arbitrary function calls supplied by the caller. This falls under Execute category because the actual effects depend on what function is passed as an argument. The severity is high because wrapping calls without proper validation could allow an AI agent to execute unintended operations on downstream systems.

From the tool's definition Tool performs 'Execute a function call' with ability to trigger external operations. The description explicitly states it executes function calls, which can have side effects depending on what function is wrapped.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wrap_call Rate-limited

wrap_call stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "wrap_call": {
      "limits": [
        {
          "counter": "wrap_call_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches SelfHeal MCP, so you can run agents against it safely.

FAQ

Questions about wrap_call

What does the wrap_call tool do? +

Execute a function call with retry, circuit breaker, and metrics. It is categorised as a Execute tool in the SelfHeal MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wrap_call? +

Register the SelfHeal MCP server in PolicyLayer and add a rule for wrap_call: 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 SelfHeal MCP. Nothing to install.

What risk level is wrap_call? +

wrap_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit wrap_call? +

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

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

wrap_call is provided by the SelfHeal MCP server (selfheal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.