AI agents use send_message_to_group to create or update resources in Signal MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Signal MCP environment.
This tool creates/sends a message, which is a write operation that modifies data (adds a message to a group) reversibly. While message sending has real-world consequences (communication side effects), it is not destructive (messages can be deleted), not financial, and not code execution.
From the tool's definition Tool description explicitly states it will 'Send a message to a group using signal-cli.' The action modifies the state of group communication by adding a new message.
Documented attack patterns abuse exactly the kind of access send_message_to_group gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Signal MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for send_message_to_group:
{
"version": "1",
"default": "deny",
"tools": {
"send_message_to_group": {
"limits": [
{
"counter": "send_message_to_group_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_message_to_group 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 message to a group using signal-cli. It is categorised as a Write tool in the Signal MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Signal MCP server in PolicyLayer and add a rule for send_message_to_group: 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 Signal MCP. Nothing to install.
send_message_to_group 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_message_to_group 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_message_to_group. 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_message_to_group is provided by the Signal MCP server (rymurr/signal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Signal MCP, 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.
3 Signal MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.