Measure adherence to constraints and safety instructions
AI agents call safety.assess_instruction_following to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs measurement and assessment—a read-only activity that retrieves or analyzes information about safety compliance. It does not create, modify, delete, or execute actions; it evaluates existing state. The low severity reflects that misuse would produce informational output only, with no side effects on data, systems, or finances.
From the tool's definition Tool name 'assess_instruction_following' and description 'Measure adherence to constraints and safety instructions' indicate a diagnostic/audit operation that queries or evaluates compliance state without modifying systems, executing code, or triggering…
Attacks that exploit this kind of access
Measure adherence to constraints and safety instructions. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for safety.assess_instruction_following: 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 ContextForge MCP Gateway. Nothing to install.
safety.assess_instruction_following 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 safety.assess_instruction_following 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 safety.assess_instruction_following. 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.
safety.assess_instruction_following is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). 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 →