check_agent_score
AI agents call check_agent_score to retrieve information from Thoughtproof without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The naming pattern and context of a verification/reasoning server indicate this tool likely retrieves or queries existing agent scores rather than modifying, deleting, or executing operations. With an empty description, confidence is moderate but the 'check' verb and '_score' suffix strongly indicate a read-only lookup operation. No evidence of side effects, irreversibility, or financial impact.
From the tool's definition Tool name 'check_agent_score' suggests data retrieval/querying of a scoring metric. The description is empty, limiting direct evidence of capabilities.
Attacks that exploit this kind of access
check_agent_score. It is categorised as a Read tool in the Thoughtproof MCP Server, which means it retrieves data without modifying state.
Register the Thoughtproof MCP server in PolicyLayer and add a rule for check_agent_score: 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 Thoughtproof. Nothing to install.
check_agent_score 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 check_agent_score 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 check_agent_score. 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.
check_agent_score is provided by the Thoughtproof MCP server (thoughtproof/thoughtproof-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 →