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 MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
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.
tools:
clark_ai_coach:
rules:
- action: allowSee the full Gridually policy for all 7 tools.
Agents calling read-class tools like clark_ai_coach have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
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.
Add a rule in your Intercept YAML policy under the tools section for clark_ai_coach. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Gridually MCP server.
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 Intercept 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 Intercept 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). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept