send_contact · Claudegram MCP: Risk & Policy

WHAT IT DOES

What send_contact does on Claudegram

AI agents use send_contact to create or update resources in Claudegram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claudegram environment.

WHY IT NEEDS A POLICY

Why send_contact needs a policy

This tool writes/creates a new message in a chat with contact information. It is reversible (messages can be deleted), so it falls under Write rather than Destructive. The severity is medium because misuse could involve sharing someone's contact details without consent, but the impact is limited to message creation in accessible chats rather than system-wide data corruption or financial harm.

From the tool's definition Tool name 'send_contact' and description 'Отправить визитку контакта' (Send a contact card/business card) indicate the tool creates and sends a contact record to a Telegram chat, modifying conversation state by adding a message.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_contact Rate-limited

send_contact stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_contact": {
      "limits": [
        {
          "counter": "send_contact_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about send_contact

What does the send_contact tool do? +

Отправить визитку контакта. It is categorised as a Write tool in the Claudegram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_contact? +

Register the Claudegram MCP server in PolicyLayer and add a rule for send_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 Claudegram. Nothing to install.

What risk level is send_contact? +

send_contact is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_contact? +

Yes. Add a rate_limit block to the send_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 send_contact completely? +

Set action: deny in the PolicyLayer policy for send_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 send_contact? +

send_contact is provided by the Claudegram MCP server (sanjar-x/claudegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.