mcp

Create run key

create_run_key

Mints a key for one run's runner: it reaches ONLY that run's machines, volumes and networks, everything it creates joins the run, it works only through this MCP (connect with the header Authorization: Bearer ), and it is deleted when the run ends. Use it instead of an account key for an agent that works inside a run. Usage is billed to the account. The key is shown once. Needs a logged-in session or a full-access key; a run key cannot mint one.

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": {
      "id": "<id>"
    },
    "name": "create_run_key"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	The run's id, from create_run or list_runs.
`expires_in_hours`	No	Optional lifetime in hours, 1 to 168 (7 days). Default 24.

Output Schema

Name	Required	Description	Default
`mode`	No
`next`	No
`error`	No
`result`	No
`status`	No
`details`	No
`machine`	No
`message`	No
`request`	No
`recovery`	No
`duplicate`	No
`plan_tool`	No
`needs_plan`	No
`validation`	No
`needs_keypair`	No
`account_notices`	No
`idempotency_key`	No
`source_mismatch`	No
`available_keypairs`	No
`needs_keypair_name`	No
`invalid_keypair_name`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false). It discloses the containment boundary, the transport constraint ('works only through this MCP (connect with the header Authorization: Bearer <key>)'), the lifecycle ('deleted when the run ends'), the one-time display of the secret, and the billing implication.

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

Conciseness4/5

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

Front-loaded and dense with useful content, with the scope and substitution guidance appearing first. The opening sentence is a long comma-spliced run-on bundling four distinct facts, which slightly hurts scannability, but no clause is filler.

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

Completeness5/5

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

For a two-parameter credential-minting tool with an output schema, everything an agent needs is present: scope of the credential, auth requirement, lifespan, billing, and the one-time visibility caveat. Return-value details are correctly left to the output schema.

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 coverage is 100% and both parameters are already documented in-schema, including the id's provenance ('from create_run or list_runs') and the 1-168 hour range with a 24-hour default. The description adds no parameter-level detail, so the baseline of 3 applies.

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

Purpose5/5

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

States a specific verb and resource ('Mints a key for one run's runner') and immediately bounds its scope: it reaches only that run's machines, volumes and networks. This is clearly distinguishable from the sibling create_api_key, which the description implicitly contrasts as an 'account key'.

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

Usage Guidelines5/5

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

Explicitly names the alternative and the condition selecting it: 'Use it instead of an account key for an agent that works inside a run.' It also states the prerequisite for calling it ('Needs a logged-in session or a full-access key; a run key cannot mint one'), covering the main when-to-use and when-not-to-use cases.

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

All mcp 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?