Skip to main content
Glama
Sign In
openapi-lookup-mcp

openapi-lookup-mcp

by fredarcito
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Get API schema details

get_schema
Read-only

Retrieve one API schema by name as a compact summary with referenced schemas and the endpoints that use it, so you can inspect a data model or find where it is accepted or returned.

Instructions

Show one schema (data model) of the API by name as a compact summary with the schemas it references, followed by the endpoints that use it. Use it to read a model without going through an endpoint, or to find which endpoints accept or return it.

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": {
      "name": "<name>"
    },
    "name": "get_schema"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNoReturn the original spec YAML instead of the summary; use only when the summary lacks a detail
nameYesSchema name, e.g. CandidateProfile
refreshNoDownload the spec again first; use when the result does not match the API's real behaviour

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds genuine value by disclosing the composition of the result (summary plus references plus consuming endpoints). It also explains the two behavioral flags in prose terms – raw yields the original spec YAML, refresh re-downloads when results don't match real behaviour – though it doesn't discuss size limits or pagination of the endpoint list.

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 sentences, front-loaded with the operation and its output shape, and the second sentence exists solely to give usage context – nothing is wasted. The first sentence is clause-dense but reads linearly without ambiguity.

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

Completeness5/5

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

With no output schema, the description carries the burden of explaining return values and does so concretely (summary, referenced schemas, endpoints using it). Combined with a fully documented three-parameter schema and readOnly annotations, an agent has everything needed to call it correctly.

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 description coverage is 100% and the parameter descriptions already explain when to use raw and refresh, so the schema does the heavy lifting. The description only reinforces that lookup is "by name"; it adds no format or naming-convention detail beyond the schema's own example.

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 ("Show one schema (data model) of the API by name") and goes further to describe the shape of the answer: a compact summary, its referenced schemas, then the endpoints that use it. That specificity lets an agent distinguish it from get_endpoint, which would retrieve the model through an endpoint instead.

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 two concrete situations to reach for it: reading a model without going through an endpoint, and discovering which endpoints accept or return it. It implies the alternative path (endpoint-based reading) rather than naming a sibling tool outright, so it stops short of full when/when-not routing.

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