AI agents invoke session_connect to trigger actions in Pernosco. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation — opening a browser tab in Firefox and connecting to a remote debugging session. It doesn't merely read data; it initiates a browser action and establishes a session, which qualifies as Execute. Misuse could open arbitrary URLs in the browser.
From the tool's definition 'Connect to a Pernosco trace by URL or trace ID. Opens the tab in Firefox if not already open.'
Attacks that exploit this kind of access
Connect to a Pernosco trace by URL or trace ID. Opens the tab in Firefox if not already open. It is categorised as a Execute tool in the Pernosco MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pernosco MCP server in PolicyLayer and add a rule for session_connect: 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.
session_connect is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the session_connect 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 session_connect. 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.
session_connect 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 →