Build the system-prompt-ready coach instructions for a Tough Customer
AI agents call get_coach_context to retrieve information from Tough Customer MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration or instruction data for a roleplay coach persona. It has no side effects, does not modify data, execute code, delete resources, or commit financial transactions. It is purely a read operation that supplies context/instructions for use elsewhere in the system.
From the tool's definition The tool 'get_coach_context' retrieves and builds 'system-prompt-ready coach instructions' — it fetches or constructs data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Build the system-prompt-ready coach instructions for a Tough Customer. It is categorised as a Read tool in the Tough Customer MCP MCP Server, which means it retrieves data without modifying state.
Register the Tough Customer MCP server in PolicyLayer and add a rule for get_coach_context: 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 Tough Customer MCP. Nothing to install.
get_coach_context 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_coach_context 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_coach_context. 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_coach_context is provided by the Tough Customer MCP server (toughcustomerai/mcp). 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 →