Learn about Clark, an AI memory coach that tracks learning progress, identifies weak spots, assigns targeted practice, and provides progress reports. Available for individual learners and for teachers/schools via Tutually.
Part of the Gridually server.
Free to start. No card required.
AI agents call clark_ai_coach to retrieve information from Gridually without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though clark_ai_coach only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"clark_ai_coach": {}
}
}See the full Gridually policy for all 7 tools.
These attack patterns abuse exactly the kind of access clark_ai_coach gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Learn about Clark, an AI memory coach that tracks learning progress, identifies weak spots, assigns targeted practice, and provides progress reports. Available for individual learners and for teachers/schools via Tutually.. It is categorised as a Read tool in the Gridually MCP Server, which means it retrieves data without modifying state.
Register the Gridually MCP server in PolicyLayer and add a rule for clark_ai_coach: 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 Gridually. Nothing to install.
clark_ai_coach 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 clark_ai_coach 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 clark_ai_coach. 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.
clark_ai_coach is provided by the Gridually MCP server (gridually-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Gridually tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.