mcp-openapi-bridge: Instructions file for Claude Code

CLAUDE.md

mcp-openapi-bridge CLAUDE.md is an instructions file for Claude Code from murilojrpereira/mcp-openapi-bridge. It costs 648 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that turns an OpenAPI 3.x description into tools for MCP clients. OpenAPI is a standard document describing web APIs; MCP is a way for AI clients to call tools.

In plain words
What is it for?
Use them when working on the server’s TypeScript source, tests, builds, linting, formatting, authentication, or HTTP request handling. Live tests and releases should only happen when requested.
Why use it?
They give an agent the project’s layout, commands, conventions, and safety limits so it can make changes without running live network tests or releasing files unexpectedly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is murilojrpereira/mcp-openapi-bridge's own configuration. It tells Claude Code how to work on mcp-openapi-bridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-openapi-bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to murilojrpereira/mcp-openapi-bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/murilojrpereira/mcp-openapi-bridge/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/murilojrpereira/mcp-openapi-bridge

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-openapi-bridge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/murilojrpereira/mcp-openapi-bridge/claude-md/github.svg)](https://agentmods.dev/instructions/murilojrpereira/mcp-openapi-bridge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/murilojrpereira/mcp-openapi-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/murilojrpereira/mcp-openapi-bridge/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-openapi-bridge CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/murilojrpereira/mcp-openapi-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/murilojrpereira/mcp-openapi-bridge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 648 This file is loaded in full into every session.
When invoked 648 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00648 $0.00648
Opus 5.5 $0.00259 $0.00259
Sonnet 5.5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 1mo ago against content hash cadb2565d2bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-openapi-bridge CLAUDE.md scanned grade A with 0 findings 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 1mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

MCP server that bridges any OpenAPI 3.x REST API to MCP clients: it loads a spec, registers one tool per operation, and executes the HTTP calls. Published to npm and the MCP Registry as mcp-openapi-bridge. See README.md for usage and docs/architecture.md for design rationale.

Commands

npm run build       # tsc → dist/
npm test            # vitest, fully mocked, no network
npm run lint        # eslint src/
npm run format      # prettier --check
npm run format:fix  # prettier --write

npm run test:live makes real network calls (public Petstore). Only run it when asked.

Layout (src/)

File Responsibility
index.ts Entry point. stdio by default; MCP_TRANSPORT=http starts the HTTP transport
schema.ts Loads the spec, resolves $refs
tools.ts Turns operations into tool names, descriptions and argument schemas
zod.ts JSON Schema → Zod (schemaToZod)
executor.ts Builds URLs and performs the HTTP requests
auth.ts Auth config and headers (applyAuth, resolveAuthConfig)
types.ts Shared types

Tests live in src/__tests__/ and mock fetch with vi.stubGlobal.

Conventions

  • ESM with module: Node16: relative imports must end in .js (import ... from "./tools.js").
  • ESLint uses eslint-plugin-perfectionist (recommended-alphabetical): imports, object keys and similar are kept sorted. Run npm run lint:fix rather than reordering by hand.
  • Secrets (tokens, API keys, custom header values) must never appear in error text or tool output. See docs/architecture.md.
  • If you add, remove or rename an environment variable, update the README table and environmentVariables in server.json.
  • Add a ## [Unreleased] entry to CHANGELOG.md for user-visible changes.

Releasing: do not do this unprompted

Publishing to npm and the MCP Registry is irreversible (npm versions cannot be reused). Never run npm publish, mcp-publisher publish, or trigger the Bump Version / Release workflows unless the user explicitly asks.

Read the full file on GitHub · 56 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. 1mo ago First seen · 56 lines · 648 tokens per session scan A cadb2565d2bf

Subscribe to this mod's changes

mcp-openapi-bridge CLAUDE.md is an instructions file published in the GitHub repository murilojrpereira/mcp-openapi-bridge (0 stars, last pushed 5d ago), licensed MIT. It adds 648 tokens to every session, about $0.0026 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.

Related

mcp-openapi-bridge CLAUDE.md compared with instructions from other repositories

mcp-openapi-bridge CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-openapi-bridge CLAUDE.mdmurilojrpereira/mcp-openapi-bridgeInstructions file05d agoMITA648Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot