AI agents call get_sent_messages to retrieve information from CoordMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves previously sent messages from shared memory, which is a read-only operation with no side effects. Even if an AI agent misuses it by reading all messages, the blast radius is limited to information disclosure within the project context, posing minimal security risk compared to tools that modify state (Write), execute operations (Execute), or delete data (Destructive).
From the tool's definition Tool name 'get_sent_messages' indicates retrieval of message history with no modification capability. The description is empty, but the naming convention and context within a coordination server (where broadcast_message exists as a separate tool) strongly…
Attacks that exploit this kind of access
get_sent_messages. It is categorised as a Read tool in the CoordMCP MCP Server, which means it retrieves data without modifying state.
Register the Coord MCP server in PolicyLayer and add a rule for get_sent_messages: 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 CoordMCP. Nothing to install.
get_sent_messages 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 get_sent_messages 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 get_sent_messages. 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.
get_sent_messages is provided by the Coord MCP server (siddiquesahabaj/coordmcp). 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 →