AI agents call read_coach_memory to retrieve information from MCPacer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve stored coaching memory or historical coaching data from the MCPacer system. The 'read_' prefix strongly suggests a read-only operation with no side effects. While the empty description reduces confidence slightly, the naming convention and sibling tools indicate this is a query/retrieval function consistent with the Read category.
From the tool's definition Tool name 'read_coach_memory' contains 'read', indicating data retrieval. Description is empty, but context from sibling tools (get_activities, get_activity_by_id, get_activity_description, get_activity_streams) and the server's purpose (personalized training…
Documented attack patterns abuse exactly the kind of access read_coach_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPacer, and nothing reaches the server without passing your rules. This is the rule we recommend for read_coach_memory:
{
"version": "1",
"default": "deny",
"tools": {
"read_coach_memory": {}
}
}read_coach_memory 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.
read_coach_memory. It is categorised as a Read tool in the MCPacer MCP Server, which means it retrieves data without modifying state.
Register the MCPacer MCP server in PolicyLayer and add a rule for read_coach_memory: 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 MCPacer. Nothing to install.
read_coach_memory 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 read_coach_memory 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 read_coach_memory. 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.
read_coach_memory is provided by the MCPacer MCP server (wernerpe/mcpacer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCPacer, 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.
32 MCPacer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.