Log a pressure event when reality differs from expectation. Call this IMMEDIATELY when you encounter something unexpected: - Something failed that you predicted would work - You had to change approach mid-implementation - You discovered a constraint not in your initial context This is the primary...
AI agents use log_pressure to create or update resources in Decision OS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Decision OS MCP environment.
This tool creates a new record (a 'pressure event') in the system when an unexpected outcome occurs. It writes data to the decision tracking system but does not delete, execute code, or involve financial transactions. The data is presumably reversible or at least additive.
From the tool's definition Log a pressure event when reality differs from expectation... This is the primary learning mechanism. Be specific about what you expected vs what happened.
Attacks that exploit this kind of access
Log a pressure event when reality differs from expectation. Call this IMMEDIATELY when you encounter something unexpected: - Something failed that you predicted would work - You had to change approach mid-implementation - You discovered a constraint not in your initial context This is the primary learning mechanism. Be specific about what you expected vs what happened. It is categorised as a Write tool in the Decision OS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Decision OS MCP server in PolicyLayer and add a rule for log_pressure: 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 Decision OS MCP. Nothing to install.
log_pressure is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the log_pressure 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 log_pressure. 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.
log_pressure is provided by the Decision OS MCP server (marianstefi20/decision-os-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 →