A detailed tool for systematic self-monitoring of knowledge and reasoning quality. This tool helps models track knowledge boundaries, claim certainty, and reasoning biases. It provides a framework for metacognitive assessment across various domains and reasoning tasks.
Risk signalsHigh parameter count (29 properties)
Part of the Clear Thought Server server.
Free to start. No card required.
AI agents call metacognitivemonitoring to perform operations in Clear Thought Server. While the risk category is not fully classified, applying a rate limit gives you visibility into how often the tool is called and prevents unexpected bursts of activity from autonomous agents.
Applying a policy to metacognitivemonitoring gives you an audit trail of every call an AI agent makes. Even for low-risk tools, visibility into agent behaviour helps you debug issues, optimise workflows, and maintain compliance with your organisation's security requirements.
Apply a rate limit to control usage and monitor for unexpected behaviour.
{
"version": "1",
"default": "deny",
"tools": {
"metacognitivemonitoring": {
"limits": [
{
"counter": "metacognitivemonitoring_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
}See the full Clear Thought Server policy for all 11 tools.
These attack patterns abuse exactly the kind of access metacognitivemonitoring gives an agent. Each links to the full case and the policy that stops it:
Other other tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
A detailed tool for systematic self-monitoring of knowledge and reasoning quality. This tool helps models track knowledge boundaries, claim certainty, and reasoning biases. It provides a framework for metacognitive assessment across various domains and reasoning tasks.. It is categorised as a Other tool in the Clear Thought Server MCP Server, which means it performs auxiliary operations.
Register the Clear Thought Server MCP server in PolicyLayer and add a rule for metacognitivemonitoring: 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 Clear Thought Server. Nothing to install.
metacognitivemonitoring is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the metacognitivemonitoring 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 metacognitivemonitoring. 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.
metacognitivemonitoring is provided by the Clear Thought Server MCP server (ThinkFar/clear-thought-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Clear Thought Server 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.