Fetch Hive

Publish an MCP gateway

publish_gateway

Put the draft live at the gateway's URL, for every MCP client using it. Call it first without approved to see what goes live and any blocking problems, tell the person, and call again with approved: true only after they say yes. MCP clients then need a token, which the person creates on the dashboard (links.tokens).

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": {
      "gateway_id": "<gateway_id>"
    },
    "name": "publish_gateway"
  }
}

Input Schema

Name	Required	Description	Default
`approved`	No	true only after the person has agreed to publish.
`gateway_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Beyond the annotations, the description discloses that publishing affects every MCP client at the live URL, that a dry-run mode exists, and that human approval gates the real write. It does not state whether publishing replaces an existing live version or how to undo it, even though unpublish_gateway and rollback_gateway exist as siblings, so reversibility is left implicit.

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?

Three short sentences, front-loaded with the effect of the call, then the call protocol, then the follow-on token requirement. Every clause carries actionable information and nothing is padded.

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?

With no output schema, the description correctly summarizes what the unapproved call returns ('what goes live and any blocking problems'). It is nearly complete for a two-parameter mutation, with the only real gap being the absence of any statement about undoing a publish or how it interacts with an already-live gateway.

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 50%, and 'gateway_id' carries no description anywhere, so the description does not clarify which gateway identifier is expected. It does, however, add substantial meaning to 'approved' beyond the schema's one-line note by explaining it as the second step of a preview-then-confirm sequence.

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?

The description names a specific verb and resource ('Put the draft live at the gateway's URL') and states the blast radius ('for every MCP client using it'), which is more precise than the title alone. An agent can immediately distinguish this from read-side siblings like get_gateway or list_gateway_logs.

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?

It prescribes an explicit two-call protocol: first without 'approved' to preview effects and blockers, then again with 'approved: true' only after the person consents. That is an unambiguous when-to-call-which-way rule, and it also flags the downstream token prerequisite the person must satisfy on the dashboard.

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

All Fetch Hive tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?