openapi

Archived TypeScript library that converts Swagger/OpenAPI (v2.0, v3.0, v3.1) documents into type-safe schemas suitable for LLM function calling. It normalizes specs through an “emended” OpenAPI v3.1 intermediate format, and includes runtime validation (via typia integration) to validate/repair LLM-generated arguments. It also references MCP-related integration and adapters for common LLM tooling ecosystems.

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ Ai Ml api openapi swagger llm-function-calling typescript validation mcp structured-output schema-conversion
⚙ Agent Friendliness
60
/ 100
Can an agent use this?
🔒 Security
46
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
35
Documentation
75
Error Messages
--
Auth Simplicity
95
Rate Limits
10

🔒 Security

TLS Enforcement
60
Auth Strength
35
Scope Granularity
30
Dep. Hygiene
50
Secret Handling
60

TLS enforcement is not explicitly specified in provided content; examples use http://localhost for development. Auth strength is mainly dependent on your integration with external LLM providers and your backend; the library itself doesn’t describe access controls. Validation of model-generated arguments can reduce injection/type confusion risks, but you should still treat all LLM/tool inputs as untrusted and apply server-side authorization and input sanitization.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
20
Error Recovery
55
AF Security Reliability

Best When

You already have an OpenAPI spec and want strongly typed, validated LLM function-calling schemas, and you are able to migrate to the maintained typia equivalents.

Avoid When

You need long-term maintenance/support from this specific package, or you require guaranteed, documented runtime error semantics for HTTP execution beyond what’s shown in the archived docs.

Use Cases

  • Convert an existing REST API described by OpenAPI/Swagger into LLM tool/function-callable schemas.
  • Generate provider-agnostic function/tool parameter schemas for multiple LLMs (OpenAI/Claude/etc.).
  • Add runtime validation of model-generated JSON arguments before executing backend HTTP calls.
  • Normalize and transform between OpenAPI versions (including to an “emended” v3.1 format).

Not For

  • Acting as an HTTP server/API gateway for your backend (it’s a schema/conversion + client-side execution helper, not an API hosting service).
  • Production adoption for new projects (repo is archived and functionality merged into typia; no longer maintained).

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
Yes
Webhooks
No

Authentication

Methods: No authentication described for the library itself (it generates schemas and performs client-side operations). OAuth/API-key authentication is only relevant to the external LLM provider clients you integrate separately (e.g., OpenAI SDK).
OAuth: No Scopes: No

No built-in auth mechanism is described for this package. Example code shows passing API keys to the external LLM client (e.g., OpenAI), and HTTP connection details to your backend (host URL), but not auth handling inside this library.

Pricing

Free tier: No
Requires CC: No

Open-source npm package; pricing not indicated in provided data.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Package is archived; functionality is merged into typia—ensure you use maintained replacements for production.
  • LLM tool calling may produce type mismatches; you should perform validation and feed errors back to the model as shown.
  • HTTP execution depends on your backend availability/behavior; the library does not appear to document retry/idempotency semantics for safe replays.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for openapi.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered