AI agents call dynamic_annotations 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 is a read-only inspection tool that queries and displays execution trace information from a Pernosco debugging session. It has no capability to modify state, delete data, execute code, or trigger external actions. The blast radius of misuse is minimal—worst case an agent gains better visibility into debugged code execution, which does not cause harm.
From the tool's definition Tool shows/displays execution counts and which lines executed; no side effects. The description uses only query/inspection language: 'Show which lines...executed', 'understanding code paths'.
Attacks that exploit this kind of access
Show which lines of the current source file executed at the current focus, with execution counts for loops. Essential for understanding which code paths and branches ran. 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 dynamic_annotations: 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.
dynamic_annotations 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 dynamic_annotations 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 dynamic_annotations. 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.
dynamic_annotations 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 →