send_conversation_message

THE RISK

Medium Risk

Why send_conversation_message needs a policy

This is a Write operation because it creates new communication data that is stored and delivered. Severity is medium because while messages can be sent to multiple people at scale, they are reversible (can be acknowledged/clarified), do not directly manipulate financial data or critical system state, and the blast radius is limited to conversation context rather than system-wide impact.

From the tool's definition Tool performs 'Post a message into a Conversation' which creates new data (a message) that is distributed to multiple participants. Description confirms it writes/sends data ('Fanned out to all participants via their channel').

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

POLICY

How to control send_conversation_message

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for send_conversation_message:

policy.json

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

send_conversation_message 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.

Create a free account and register Mcp Ap2 — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Mcp Ap2 tools

Financial authorize_transaction Authorize a transaction (reserve funds without capturing) via Braintree GraphQL authorizeP Financial block_card Block a card temporarily (reversible). Use for lost-card or fraud-suspected flows. Card st Financial cancel_bill Cancel a pending bill Financial cancel_collection Cancel a scheduled collection request Financial cancel_credit Cancel an authorized-but-uncaptured credit payment. Financial cancel_debit Cancel a debit-card payment by Getnet payment_id. Financial cancel_invoice Cancel/void an authorized invoice (FECancel — limited to certain types/conditions) Financial cancel_order Cancel an order, optionally restocking and refunding

All 1300 Mcp Ap2 tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about send_conversation_message

What does the send_conversation_message tool do? +

Post a message into a Conversation. Fanned out to all participants via their channel (SMS / WhatsApp / chat). It is categorised as a Write tool in the Mcp Ap2 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_conversation_message? +

Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for send_conversation_message: 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 Ap2. Nothing to install.

What risk level is send_conversation_message? +

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

Can I rate-limit send_conversation_message? +

Yes. Add a rate_limit block to the send_conversation_message 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_conversation_message completely? +

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

send_conversation_message is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Ap2 tool call.

Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →