Returns all targets, skills, webhooks, memories, wiki pages, and vaults. Call at session start if not already provided by a SessionStart hook.
AI agents call bootstrap to retrieve information from Shellgate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration and session data (targets, skills, webhooks, memories, wiki pages, vaults) at session start. It performs no writes or mutations. However, the data returned is sensitive — it exposes credentials/vaults, attack surface targets, and memory — so misuse could enable further high-severity actions, warranting a medium severity rating despite being a read operation.
From the tool's definition Returns all targets, skills, webhooks, memories, wiki pages, and vaults
Documented attack patterns abuse exactly the kind of access bootstrap gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Shellgate, and nothing reaches the server without passing your rules. This is the rule we recommend for bootstrap:
{
"version": "1",
"default": "deny",
"tools": {
"bootstrap": {}
}
}bootstrap is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Returns all targets, skills, webhooks, memories, wiki pages, and vaults. Call at session start if not already provided by a SessionStart hook. It is categorised as a Read tool in the Shellgate MCP Server, which means it retrieves data without modifying state.
Register the Shellgate 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 Shellgate. Nothing to install.
bootstrap 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 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 Shellgate MCP server (matthiastjong/shellgate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Shellgate, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
31 Shellgate tools catalogued and risk-classified — across an index of 43,000+ MCP servers.