openstack-mcp-server

List catalog endpoints

list_endpoints

Read-onlyIdempotent

Lists Keystone catalog endpoints with interface and URL, filtering by region, service, project, and interface; a forbidden response means the role is missing, not that the list is empty.

Instructions

List Keystone catalog endpoints with interface and URL. Usually needs more than a project reader role; forbidden means the role is missing, not that the list is empty. Not paged; narrow with filters.

Input Schema

Name	Required	Description
`limit`	No	Maximum items to return (1-100, default 50).
`interface`	No
`region_id`	No
`project_id`	No	Project ID to work in; omit for the default project. Allowed values are listed by get_scope.
`service_id`	No

Output Schema

Name	Required	Description
`items`	Yes
`limit`	Yes	Maximum number of items requested.
`complete`	Yes	True when no more items exist beyond this page.
`resource`	Yes	Resource type of the items.
`project_id`	Yes	Project whose session produced the list.
`next_marker`	No	Pass as marker to read the next page; null when complete or when the API has no marker paging.
`observed_at`	Yes	UTC time the list was read.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 30, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds two genuinely useful behaviors: an elevated role is usually required, and 403/forbidden means a missing role rather than an empty result. The "not paged" note also prevents a wrong pagination assumption. Return shape is left to the output schema.

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, front-loaded sentences with no filler; the scope statement comes first and the caveats follow. The opening phrase "with interface and URL" is slightly ambiguous about whether interface is a filter or a returned field.

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?

The output schema covers return values and annotations cover the safety profile, so the remaining burden is parameter meaning. For a five-parameter filtered list where three filters are undocumented anywhere, the description leaves an agent guessing how to narrow the result.

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

Parameters2/5

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

Schema coverage is only 40%: interface, region_id and service_id have no schema descriptions, and the description does not explain them at all. "Narrow with filters" is a generic gesture that never says which filter to use for which narrowing goal, so the description fails to compensate for the coverage gap.

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?

States a specific verb and resource ("List Keystone catalog endpoints") and notes the fields returned. It does not, however, distinguish this from the sibling list_services, which an agent could easily confuse with catalog endpoints.

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?

"Not paged; narrow with filters" plus the role caveat gives clear operational context for when and how to call it. It stops short of naming an alternative (e.g. list_services) for the case where the catalog view is the wrong resource.

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