AI agents call watch_variable to retrieve information from Pernosco without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical metadata about variable writes from a debugging session trace without modifying any state. It queries execution trace data to provide a history of writes to a specific variable's memory address. While it involves tracing execution, it does not execute new code or commands—it only inspects and retrieves pre-recorded execution information.
From the tool's definition Tool description states it 'Get[s] the complete write history' and 'traces all writes' of a variable. The word 'Get' and 'traces' indicate data retrieval operations.
Attacks that exploit this kind of access
Get the complete write history of a C++ variable. Evaluates the expression to find its memory address, then traces all writes. Simpler than manually using evaluate + watchpoint_history. It is categorised as a Read tool in the Pernosco MCP Server, which means it retrieves data without modifying state.
Register the Pernosco MCP server in PolicyLayer and add a rule for watch_variable: 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 Pernosco. Nothing to install.
watch_variable 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 watch_variable 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 watch_variable. 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.
watch_variable is provided by the Pernosco MCP server (jnjaeschke/pernosco-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 →