Avaliação CEGA de copy sem contexto de geração. Problema: Artificial Hivemind (79% similaridade) Solução: Crítico avalia APENAS o artefato final Critérios: 1. Impacto Emocional (1-10) - Faz SENTIR ou apenas entender? 2. Especificidade (1-10) - Números, nomes, exemplos concretos? 3. Autenticidade ...
AI agents call blind_critic to retrieve information from Copywriting MCP Server 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 data (copywriting text) to generate feedback and evaluation scores. It has no capability to create, modify, delete, or execute external operations. Even though it provides critique that may inform decisions, the tool itself only reads input and returns analytical output—a classic Read operation with no state changes or irreversible consequences.
From the tool's definition The tool performs 'blind critique' (Avaliação CEGA) of copywriting artifacts. It evaluates copy against criteria (emotional impact, specificity, authenticity) and returns numerical scores and a pass/review/redo verdict.
Attacks that exploit this kind of access
Avaliação CEGA de copy sem contexto de geração. Problema: Artificial Hivemind (79% similaridade) Solução: Crítico avalia APENAS o artefato final Critérios: 1. Impacto Emocional (1-10) - Faz SENTIR ou apenas entender? 2. Especificidade (1-10) - Números, nomes, exemplos concretos? 3. Autenticidade (1-10) - Parece humano ou IA genérica? Thresholds: - Média ≥8: APROVADO - Média 6-7: REVISAR - Média <6: REFAZER. It is categorised as a Read tool in the Copywriting MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Copywriting MCP Server MCP server in PolicyLayer and add a rule for blind_critic: 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 Copywriting MCP Server. Nothing to install.
blind_critic 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 blind_critic 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 blind_critic. 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.
blind_critic is provided by the Copywriting MCP Server MCP server (lckx777/copywriting-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 →