Adjust security evaluation criteria dynamically to better align with user workflow patterns. Allows modifying, appending, or overwriting criteria text with automatic backup functionality.
AI agents call adjust_criteria to retrieve information from MCP Shell Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though adjust_criteria only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Adjust security evaluation criteria dynamically to better align with user workflow patterns. Allows modifying, appending, or overwriting criteria text with automatic backup functionality. It is categorised as a Read tool in the MCP Shell Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Shell Server MCP server in PolicyLayer and add a rule for adjust_criteria: 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 MCP Shell Server. Nothing to install.
adjust_criteria 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 adjust_criteria 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 adjust_criteria. 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.
adjust_criteria is provided by the MCP Shell Server MCP server (mako10k/mcp-shell-server). 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 →