bootkey

Boot a new agent

boot_agent

Destructive

Boots a new agent on its own server. It costs $9 a month from the bootkey balance, billed by the hour, plus model tokens on the account's own key, and is ready in about two minutes (get_agent shows its progress).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "template": "<template>",
      "region": "<region>",
      "provider": "<provider>",
      "model": "<model>"
    },
    "name": "boot_agent"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes	Up to 40 letters, numbers, spaces or dashes.
`every`	No	Minutes between wake-ups for pulse and daynight.
`model`	Yes	A model id from get_options for that provider.
`memory`	No		files
`region`	Yes	Frankfurt, New York, San Francisco or Sydney.
`temper`	No	reactive = tool (answers when asked), pulse = worker (wakes all day), daynight = worker by day, self = alive (picks its own wake-ups).	pulse
`provider`	Yes	Must be connected on the account (get_account says which).
`template`	Yes	A template id from get_options, e.g. immune-system.
`wake_model`	No	Optional cheaper model for routine wake-ups, same provider.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (destructiveHint, openWorldHint, non-idempotent), the description discloses cost structure ($9/month billed hourly from bootkey balance, plus model tokens on the account's own key) and expected latency (~2 minutes). That is exactly the kind of billing and timing context an agent needs before committing to a billable, non-idempotent creation. It does not cover failure modes or what to do when provisioning fails, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with the primary action first, then cost, latency and the follow-up tool. Every clause carries distinct information — price, billing model, token cost, readiness time, progress check — with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nine-parameter creation tool with no output schema, the description covers the main agent-facing unknowns: cost, duration and how to track progress. It would be stronger if it hinted at what the call returns (e.g., an agent id needed for get_agent) or at failure/rollback behavior for a destructive, non-idempotent operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 89% and all nine parameters, including enums for temper, memory, region and every, are documented inline. The description adds no parameter-level meaning at all, so the schema carries the full burden and the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Boots a new agent on its own server" gives a specific verb and resource with a clear scope (provisioning, not managing). It does not explicitly contrast itself with provisioning-adjacent siblings such as add_machine or set_temper, so an agent must infer the boundary, but the core action is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a useful post-call path — "get_agent shows its progress" — which tells the agent what to do immediately after booting. It stops short of stating when to choose this tool versus alternatives or listing prerequisites (e.g., provider must be connected, template/model must come from get_options), which are only implied elsewhere.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All bootkey tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?