Gluo

Start a golive job

create_job

Hand off a multi-step, multi-day task that golive runs to completion, even after this session ends. Paid or irreversible steps pause for the user's approval through a link. Job types:

launch_domain: Buy a domain, put its DNS on the configured provider, point it at your app, and confirm it resolves and serves HTTPS. Pauses for the user to approve the purchase with their passkey. Can take minutes to hours; the job keeps running after this session ends. launch_domain input: { "domain": "example.com", "target": "my-app.vercel.app or an IPv4 address" }

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": {
      "type": "<type>",
      "input": "<input>"
    },
    "name": "create_job"
  }
}

Input Schema

Name	Required	Description
`type`	Yes
`email`	No	The user's email. Needed only if you connected without signing in: Gluo sends the approval there.
`input`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations the description must carry the full burden, and it does well: it discloses background execution past session end, human-approval gating of paid/irreversible steps via a link, passkey purchase approval, and a minutes-to-hours runtime. It omits failure behavior and how the job's progress is subsequently retrieved.

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?

Front-loaded with the core behavior and kept to a few dense sentences; each one adds new information (async lifetime, approval gate, job type, input shape). No filler.

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

Completeness3/5

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

There is no output schema, yet the description never says what is returned (presumably a job id to poll with get_job), nor how to monitor or cancel the run. Given a free-form nested input and no annotations, that missing post-call guidance is a notable gap.

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

Parameters4/5

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

Schema coverage is only 33%, and the input object is free-form with additionalProperties, so the schema documents almost nothing. The description compensates by spelling out the launch_domain input shape with example domain and target values. The email parameter's purpose is documented only in the schema, not repeated here.

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?

The description opens with a specific verb and resource: hand off an asynchronous multi-step task that golive runs to completion. It then enumerates the supported job type (launch_domain) and summarizes its pipeline. It never references the get_job/list_jobs/undo_job siblings, so the line against them is left to inference.

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 trigger condition is stated ('multi-step, multi-day task ... even after this session ends'), which is a real usage cue. However, no when-not-to-use condition is given and no alternative is named, so an agent cannot easily tell when to prefer call_api or request_service over this.

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

All Gluo 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?