request_contact · MCP Agent Mail MCP: Risk & Policy

WHAT IT DOES

What request_contact does on MCP Agent Mail

AI agents call request_contact as a supporting operation in MCP Agent Mail workflows.

WHY IT NEEDS A POLICY

Why request_contact needs a policy

With no description provided, I can only infer from the tool name. 'request_contact' suggests initiating a contact or communication request, which could be a Write operation (creating a contact request), but given the server context of agent coordination and messaging, it likely involves sending or requesting a contact/identity. Without any description, confidence is very low and defaulting to Other is safest.

From the tool's definition Tool description is empty; only the name 'request_contact' is available.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

request_contact Rate-limited

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

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "request_contact": {
      "limits": [
        {
          "counter": "request_contact_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about request_contact

What does the request_contact tool do? +

request_contact. It is categorised as a Other tool in the MCP Agent Mail MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on request_contact? +

Register the MCP Agent Mail MCP server in PolicyLayer and add a rule for request_contact: 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 MCP Agent Mail. Nothing to install.

What risk level is request_contact? +

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

Can I rate-limit request_contact? +

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

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

request_contact is provided by the MCP Agent Mail MCP server (omelchmichael/mcp_agent_mail). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.