Skip to main content
Glama
Sign In
gitlab-api

gitlab-api

by Knuckles-Team
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Gitlab Instances List

gitlab_instances_list
Read-only

Lists configured GitLab tenants by name so you can identify available instances for multi-tenant API operations; tokens are never returned.

Instructions

List the configured GitLab tenants by name (tokens are never returned).

Multi-tenancy is driven by the shared scion-sdk XDG config (gitlab_instances in ~/.config/scion-sdk/config.json). Falls back to the single-host GITLAB_URL/GITLAB_TOKEN.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "gitlab_instances_list"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv27.3.20
    • removedInput schema / properties / name
      Removed value: -{
-  "default": "",
-  "description": "Instance name for action='get'.",
-  "type": "string"
-}
  2. First observedv27.3.13

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds real behavioral context by stating tokens are never returned, that tenancy comes from the shared scion-sdk XDG config at a specific path, and that it falls back to single-host GITLAB_URL/GITLAB_TOKEN when no multi-tenancy config exists. It stops short of describing the returned record shape beyond the name.

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?

Three short lines, front-loaded with the verb and result, then the config-source detail and the fallback. The XDG path is the only mildly verbose element, but it is actionable for diagnosing why the list may be empty.

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 zero-parameter, read-only listing with no output schema, the description covers source of truth, fallback behavior, and a privacy guarantee about returned data. The only gap is not hinting at what fields accompany the tenant name (e.g. URL), which matters slightly given there is no output schema.

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?

The tool takes no parameters, so the baseline is 4; the description correctly adds nothing spurious about inputs and instead spends its words on configuration resolution, which is the only meaningful 'input' for this call.

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 — 'List the configured GitLab tenants by name' — which is immediately distinguishable from the sibling gitlab_instances_get that would fetch a single tenant's detail. The parenthetical about tokens clarifies the scope of what is enumerated.

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?

There is no explicit when-to-use or when-not-to-use statement and no named alternative, but the zero-parameter discovery nature of the tool combined with 'configured tenants' implies it is the entry point for finding which GitLab instances exist before calling instance-scoped tools. Usage is inferable rather than stated.

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

Deploy Server

Other Tools