Fetch Hive

Change an MCP gateway

update_gateway

Idempotent

Rename a gateway, set the API base URL its tools call (when the spec has none or the wrong one), or change its slug before it is first published. On a live gateway the base URL is used at once, so call without approved first, tell the person, and call again with approved: true.

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": "update_gateway"
  }
}

Input Schema

Name	Required	Description
`name`	No
`slug`	No
`approved`	No	true only after the person has agreed to change a live gateway's base URL.
`base_url`	No	https base URL of the API, e.g. https://api.example.com/v1. Empty string goes back to the spec's server.
`gateway_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare this a non-read-only, idempotent, non-destructive, closed-world mutation, and the description adds genuinely useful context: a live gateway picks up the base URL immediately. That immediate-effect warning is the key behavioral detail. It still does not say what permissions are needed, what happens to the running gateway's tools during the change, or whether the change is reversible.

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?

Two compact sentences, each with a job: the first lists what can be changed, the second front-loads the risk and the required call sequence. Some subclauses such as 'when the spec has none or the wrong one' add useful qualifiers without bloat.

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?

With five parameters and no output schema, the description must cover the shape of the interaction itself, and it covers the risky path well. However, it never states what the tool returns after a successful change, what happens to published gateway state, or error behavior, which an agent needs for anything beyond the happy path.

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 only 40%, so the description has to carry more weight, and it partly does: it explains that base_url is the API root the tools call and that an empty value reverts to the spec's server, and it explains the approved flag's two-call sequence. But name and slug are only alluded to in prose, and gateway_id gets no mention at all, so the gap is narrowed rather than closed.

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 names concrete operations on the gateway resource: rename (name), set the API base URL its tools call, and change the slug. It scopes the base URL change to the case where the spec has none or the wrong one, which implicitly separates it from the sibling update_gateway_tools, but that sibling is never named.

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

Usage Guidelines4/5

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

Gives clear when-to-use conditions: base URL changes are for specs with no or wrong server, and slug changes are for before first publish. It also prescribes the two-step approval protocol for live gateways. What is missing is explicit routing to alternatives such as update_gateway_tools, publish_gateway, or recompile_gateway when the task is not a rename or URL fix.

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?