Initialize agent session: register (if needed), get current focus, pending tasks, and recent decisions. Call this once at the start of your session.
AI agents invoke bootstrap to trigger actions in Agent Orchestration. 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.
While nominally descriptive, bootstrap operations trigger registration and session activation which constitute controlled executions. The tool reads state (pending tasks, focus) but also performs registration (Write-adjacent). Classification as Execute reflects that it triggers initialization logic whose effects depend on agent context.
From the tool's definition Tool performs initialization sequence including 'register', retrieves 'current focus' and 'pending tasks', implying system state changes and external operations.
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 Agent Orchestration, and nothing reaches the server without passing your rules. This is the rule we recommend for bootstrap:
{
"version": "1",
"default": "deny",
"tools": {
"bootstrap": {
"limits": [
{
"counter": "bootstrap_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}bootstrap stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Initialize agent session: register (if needed), get current focus, pending tasks, and recent decisions. Call this once at the start of your session. It is categorised as a Execute tool in the Agent Orchestration MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Agent Orchestration 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 Agent Orchestration. 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 Agent Orchestration MCP server (madebyaris/agent-orchestration). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Orchestration, 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.
35 Agent Orchestration tools catalogued and risk-classified — across an index of 43,000+ MCP servers.