Self-install kit for wiring THIS agent into the switchboard. Returns the one-line install command for your platform PLUS the full hook file contents, target paths, and settings.json merge — so you can either run the one-liner (via your shell) or write the files yourself. Pass your agent_id; pass ...
AI agents invoke bootstrap to trigger actions in Mcp Switchboard. 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 goes beyond simple configuration retrieval; it generates and facilitates execution of shell commands and system-level file writes (hooks, settings.json). While not destructive in the data-loss sense, it has Execute severity because: (1) it triggers external shell operations whose effects depend on the agent_id and base parameters provided, (2) it modifies system hooks and configuration in ways that persist…
From the tool's definition Tool performs 'Self-install kit for wiring THIS agent into the switchboard' and 'Returns the one-line install command for your platform' — explicitly designed to execute shell commands and write configuration files. Modifies system hooks and settings.json.
Attacks that exploit this kind of access
Self-install kit for wiring THIS agent into the switchboard. Returns the one-line install command for your platform PLUS the full hook file contents, target paths, and settings.json merge — so you can either run the one-liner (via your shell) or write the files yourself. Pass your agent_id; pass base if it differs from the default host. After installing, restart your session so the hooks load. It is categorised as a Execute tool in the Mcp Switchboard MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Switchboard MCP server in PolicyLayer and add a rule for bootstrap: 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 Mcp Switchboard. Nothing to install.
bootstrap 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 bootstrap 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 bootstrap. 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.
bootstrap is provided by the Mcp Switchboard MCP server (jemplayer82/mcp-switchboard). 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 →