apis-io

find_openapis

Read-only

OpenAPI specifications across the catalog. The REST contract. get_openapi returns one API's primary spec with optional inlined body. Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`q`	No	Free text over name + description.
`page`	No
`sort`	No	Order: relevance (catalog order), provider, or name.
`tags`	No	Tag slugs. On PROVIDERS this is identity — what the company says it does, from its own apis.yml. A resource or operation term (webhook, saml, order, oai-pmh) will correctly match no provider; use find_apis?tags= for those, or find_providers?api_tags= to reach companies whose APIs merely touch it.
`limit`	No
`match`	No		any
`context`	No	Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.
`include`	No
`providers`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 17, 2026

changedInput schema / properties / tags / description

Previous value: -"Tag slugs. On PROVIDERS this is identity — what the company says it does, from its own apis.yml. A resource or operation term (webhook, saml, order, oai-pmh) will correctly match no provider; use find_apis?tags= for those, or api_tags below."New value: +"Tag slugs. On PROVIDERS this is identity — what the company says it does, from its own apis.yml. A resource or operation term (webhook, saml, order, oai-pmh) will correctly match no provider; use find_apis?tags= for those, or find_providers?api_tags= to reach companies whose APIs merely touch it."

Changed1 schema field changedSep 4, 2026

addedInput schema / properties / sort

Added value: +{
+  "description": "Order: relevance (catalog order), provider, or name.",
+  "enum": [
+    "relevance",
+    "provider",
+    "name"
+  ],
+  "type": "string"
+}

Changed1 schema field changedSep 2, 2026

changedInput schema / properties / tags / description

Previous value: -"Tag slugs."New value: +"Tag slugs. On PROVIDERS this is identity — what the company says it does, from its own apis.yml. A resource or operation term (webhook, saml, order, oai-pmh) will correctly match no provider; use find_apis?tags= for those, or api_tags below."

Changed1 schema field changedAug 27, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.",
+  "type": "string"
+}

AddedJul 16, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations provide readOnlyHint=true, so the safety profile is covered. The description adds that include=['content'] inlines bodies, implying default returns metadata without bodies. It does not describe pagination, response shape, or default ordering, but given the annotation covers the mutation risk, the extra context is adequate but not rich.

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?

Two sentences with no filler. The purpose is front-loaded, and the key differentiators (get_openapi, find_artifacts) are mentioned efficiently. Every sentence contributes meaning.

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

Completeness2/5

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

With 9 parameters, none required, and no output schema, the description is too sparse. It does not specify what the response contains (list of spec metadata? URLs?), pagination defaults, or how parameters like match and sort interact. An agent would have to guess the return format, which is risky for correct invocation.

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 44%, and the description compensates partially by explaining that q, tags, providers are filters and include inlines content. However, it does not explain page, limit, sort, match, or context beyond what the schema already states. The description adds some value (especially the include behavior) but does not fully cover the 56% gap.

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 clearly states the tool lists OpenAPI specifications across the catalog, and distinguishes it from get_openapi (single spec) and find_artifacts (cross-type search). The verb 'find' plus resource 'OpenAPI' and scoping is specific and immediately distinguishable from many siblings.

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?

It explicitly tells the agent to use find_artifacts for cross-type search and implies get_openapi for a single spec. This covers two key alternatives, though it doesn't address other find_* tools like find_apis or find_asyncapis. Still, the guidance is concrete and actionable for the most likely confusions.

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

All apis-io tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?