openapi-mcp-ts CLAUDE.md

Project instructions for openapi-mcp-ts, a tool that turns an API description into tools an AI assistant can call. OpenAPI and Postman are formats used to describe HTTP APIs; MCP is a standard for connecting assistants to tools.

In plain words
What is it for?
Understanding and developing the bridge between REST APIs and AI assistants. It covers API specification parsing, authentication, filtering, rate-limit awareness, logging, and safe defaults such as disabling DELETE.
Why use it?
It explains the project's purpose, architecture, technology choices, and safety rules so work on the code follows the existing design.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/procoders/openapi-mcp-ts/claude-md
Clone the repo
git clone --depth 1 https://github.com/procoders/openapi-mcp-ts
Per session 1,151 This file is loaded in full into every session.
When invoked 1,151 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01151 $0.01151
Opus 5 $0.00575 $0.00575
Sonnet 5 $0.00230 $0.00230
Haiku 4.5 $0.00115 $0.00115

Measured 2d ago against content hash 3a5bc188dbb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openapi-mcp-ts CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8080/health
CLAUDE.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

openapi-mcp-ts

Universal bridge between REST APIs and AI assistants via Model Context Protocol.

What It Does

Takes an OpenAPI spec or Postman Collection and exposes every endpoint as an MCP tool. Claude (or any MCP client) can then call your API directly — no custom code, no manual tool definitions.

Why It Exists

  • Zero friction — Point at a spec, get MCP tools
  • Format agnostic — OpenAPI 3.0/3.1, Postman v2.0/v2.1, auto-detected
  • Production ready — Auth, filtering, rate limiting awareness, structured logging
  • Safe defaults — DELETE disabled, tool count warnings, smart error messages

Tech Stack

Component Technology
Runtime Node.js 20+ (ESM)
Language TypeScript (strict mode)
HTTP Server Hono
MCP Protocol @modelcontextprotocol/sdk
CLI Commander
Validation Zod
OpenAPI Parsing @apidevtools/swagger-parser
Postman Parsing postman-collection
Logging Pino

Architecture

┌─────────────────┐     ┌──────────────┐     ┌─────────────────┐
│  OpenAPI/Postman │ ──▶ │   Converter  │ ──▶ │   MCP Tools     │
│      Spec        │     │  (parser.ts) │     │ (definitions)   │
└─────────────────┘     └──────────────┘     └────────┬────────┘
                                                       │
┌─────────────────┐     ┌──────────────┐              │
│   MCP Client    │ ◀── │  MCP Handler │ ◀────────────┘
│ (Claude, etc)   │     │  (Hono SSE)  │
└─────────────────┘     └──────┬───────┘
                               │
                        ┌──────▼───────┐     ┌─────────────────┐
                        │   Upstream   │ ──▶ │   Target API    │
                        │   Proxy      │     │                 │
                        └──────────────┘     └─────────────────┘

Project Structure

src/
├── index.ts           # Entry point, server startup
├── cli.ts             # CLI argument parsing (Commander)
├── config/
│   └── loader.ts      # Config from CLI/env/file, Zod validation
├── converter/
│   ├── parser.ts      # OpenAPI/Postman → internal format
│   ├── postman-parser.ts  # Postman Collection v2.x support
│   └── tool-filter.ts # Include/exclude patterns, warnings
├── mcp/
│   ├── handler.ts     # MCP protocol, tool execution
│   └── types.ts       # MCP tool definitions
├── server/
│   ├── routes.ts      # /health, /tools, /mcp endpoints
│   └── upstream.ts    # Proxy requests to target API
└── utils/
    └── logger.ts      # Pino logger setup

Read the full file on GitHub · 129 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 129 lines · 1,151 tokens per session scan A 3a5bc188dbb8

Subscribe to this mod's changes

openapi-mcp-ts CLAUDE.md is an instructions file published in the GitHub repository procoders/openapi-mcp-ts (0 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 1,151 tokens to every session, about $0.0058 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens