AI agents invoke reload_tab to trigger actions in Pigeon. 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.
Reloading a browser tab triggers an external browser operation with real side effects: it re-executes page scripts, re-fires network requests, and resets page state. This is an action that 'runs' or 'triggers external operations' rather than merely reading data, placing it in the Execute category. Misuse could interrupt active sessions or re-trigger side-effectful page logic.
From the tool's definition Reload a dev tab via the Pigeon extension
Attacks that exploit this kind of access
Reload a dev tab via the Pigeon extension (active localhost tab by default). It is categorised as a Execute tool in the Pigeon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pigeon MCP server in PolicyLayer and add a rule for reload_tab: 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 Pigeon. Nothing to install.
reload_tab 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 reload_tab 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 reload_tab. 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.
reload_tab is provided by the Pigeon MCP server (pepperonas/pigeon). 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 →