Send a plain text message. For business-initiated conversations outside the 24h customer-service window, use send_template_message instead.
AI agents use send_text_message to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.
Sending a text message creates new data (a message record) and performs a one-way communication action with external effects (delivery to a recipient). This is reversible in principle (message can be deleted or unsent in some systems) but represents a side effect beyond pure retrieval. It does not move money (Financial), execute arbitrary code (Execute), or irreversibly destroy data (Destructive).
From the tool's definition Tool description states 'Send a plain text message' — this creates a new message/communication artifact. The constraint mentioning 'send_template_message' for business conversations indicates this tool initiates outbound communications that persist.
Documented attack patterns abuse exactly the kind of access send_text_message gives an agent:
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_text_message:
{
"version": "1",
"default": "deny",
"tools": {
"send_text_message": {
"limits": [
{
"counter": "send_text_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_text_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.
Free to start. No card required.
Send a plain text message. For business-initiated conversations outside the 24h customer-service window, use send_template_message instead. 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.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for send_text_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.
send_text_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the send_text_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.
Set action: deny in the PolicyLayer policy for send_text_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.
send_text_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.
Start from Mcp Ap2, 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.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.