AI agents call signal_search_chat to retrieve information from Signal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server's stated purpose of 'retrieving Signal messages' and the sibling tools being read-only retrieval operations, signal_search_chat is classified as a Read operation. It searches chat data but does not modify, delete, or execute external operations. Confidence is slightly reduced (0.85 rather than higher) due to the empty description, which prevents direct textual confirmation of the tool's behavior.
From the tool's definition Tool name is 'signal_search_chat' with no description provided. Sibling tools 'signal_get_chat_messages' and 'signal_list_chats' are retrieval/query operations.
Documented attack patterns abuse exactly the kind of access signal_search_chat gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Signal, and nothing reaches the server without passing your rules. This is the rule we recommend for signal_search_chat:
{
"version": "1",
"default": "deny",
"tools": {
"signal_search_chat": {}
}
}signal_search_chat is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
signal_search_chat. It is categorised as a Read tool in the Signal MCP Server, which means it retrieves data without modifying state.
Register the Signal MCP server in PolicyLayer and add a rule for signal_search_chat: 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. Nothing to install.
signal_search_chat is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the signal_search_chat 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 signal_search_chat. 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.
signal_search_chat is provided by the Signal MCP server (stefanstranger/signal-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Signal, 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 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.