Add a business insight to the memo
AI agents use append_insight to create or update resources in MCP Variance Log — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Variance Log environment.
An AI agent can call append_insight faster than any human can review — one bad instruction and it creates or modifies resources in MCP Variance Log by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Add a business insight to the memo. It is categorised as a Write tool in the MCP Variance Log MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Variance Log MCP server in PolicyLayer and add a rule for append_insight: 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 Variance Log. Nothing to install.
append_insight 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 append_insight 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 append_insight. 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.
append_insight is provided by the MCP Variance Log MCP server (truaxki/mcp-variance-log). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.