chat_activity
AI agents call chat_activity to retrieve information from Mcp Signal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the sibling tools are predominantly read operations (list_chats, read_messages, search_messages, get_status, pairing_status) and the server's stated purpose includes reading Signal messages, chat_activity most likely retrieves or queries chat activity metadata without modifying data. The empty description lowers confidence somewhat, but the naming pattern and context strongly suggest a read operation.
From the tool's definition Tool name 'chat_activity' and sibling tools include 'read_messages', 'list_chats', 'list_groups', 'search_messages' which are clearly read-only.
Attacks that exploit this kind of access
chat_activity. It is categorised as a Read tool in the Mcp Signal MCP Server, which means it retrieves data without modifying state.
Register the Mcp Signal MCP server in PolicyLayer and add a rule for chat_activity: 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 Signal. Nothing to install.
chat_activity 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 chat_activity 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 chat_activity. 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.
chat_activity is provided by the Mcp Signal MCP server (sealjay/mcp-signal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →