Debate quality scoring: rate each agent's contribution in the current debate
AI agents call score_debate to retrieve information from Claude Team MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes debate data to produce quality scores. It has no side effects on the debate, the agents, or any external systems. It does not create, modify, delete, or execute code/commands. The scoring is a read operation that evaluates existing debate contributions.
From the tool's definition The tool 'score_debate' rates each agent's contribution in the current debate. The description indicates it performs evaluation/analysis of existing debate content without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Debate quality scoring: rate each agent's contribution in the current debate. It is categorised as a Read tool in the Claude Team MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Team MCP server in PolicyLayer and add a rule for score_debate: 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 Claude Team MCP. Nothing to install.
score_debate 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 score_debate 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 score_debate. 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.
score_debate is provided by the Claude Team MCP server (lakshan12367/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 →