Sends a message to a specific browser extension by its ID
AI agents invoke skippr_send_to_extension to trigger actions in Skippr Extension MCP Server. 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 by sending a message to a running browser extension. The effects depend on the message content and how the extension handles it, making this an Execute-category action. It's not purely Read/Write since it drives external browser-side behavior.
From the tool's definition Sends a message to a specific browser extension by its ID
Attacks that exploit this kind of access
Sends a message to a specific browser extension by its ID. It is categorised as a Execute tool in the Skippr Extension MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Skippr Extension MCP Server MCP server in PolicyLayer and add a rule for skippr_send_to_extension: 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 Skippr Extension MCP Server. Nothing to install.
skippr_send_to_extension 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 skippr_send_to_extension 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 skippr_send_to_extension. 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.
skippr_send_to_extension is provided by the Skippr Extension MCP Server MCP server (skippr-hq/extension-mcp-server). 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 →