Borrowing it
Nothing to install: this file belongs to yunhwane/swagger-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yunhwane/swagger-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/yunhwane/swagger-mcpWrote 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.
[](https://agentmods.dev/instructions/yunhwane/swagger-mcp/claude-md)<a href="https://agentmods.dev/instructions/yunhwane/swagger-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yunhwane/swagger-mcp/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.
<a href="https://agentmods.dev/instructions/yunhwane/swagger-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yunhwane/swagger-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00659 | $0.00659 |
| Opus 5.5 | $0.00264 | $0.00264 |
| Sonnet 5.5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
swagger-mcp 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
An MCP server that reads Swagger/OpenAPI specs and lets MCP clients (Claude Desktop, Claude Code) explore API schemas through natural language. Projects are registered once with add_project, then queried conversationally via tools like list_apis, describe_api, and describe_component.
Commands
npm run dev # Run with tsx (dev mode)
npm run build # Build with tsup → dist/
npm run check # TypeScript type check (noEmit)
npm test # Run all tests (vitest run)
npx vitest run tests/loader.test.ts # Run a single test file
Architecture
The server exposes 6 MCP tools organized in two groups:
Project tools (src/tools/project.ts): add_project, list_projects — manage project registry.
Center tools (src/tools/center.ts): list_services, list_apis, describe_api, describe_component — the main query interface using a 4-step drill-down pattern (list services → list APIs → describe API → describe component).
Key Data Flow
- Registry (
src/registry.ts) — persists project metadata to~/.swagger-mcp/registry.json - Loader (
src/loader.ts) — fetches specs from URL or file, parses JSON/YAML, validates OpenAPI 3.x - Normalizer (
src/normalizer.ts) — resolves$refreferences recursively (with circular ref detection).resolveShallow()preserves component-level$refs for the center tools' drill-down pattern - SpecCache (
src/spec-cache.ts) — LRU cache (max 20, 5min TTL) for parsed OpenAPI docs
Important Patterns
- Center tools use shallow resolution (
resolveShallow) — properties are expanded one level but component schema$refs are preserved. This lets the LLM decide which schemas to drill into viadescribe_component. - Tool return values use MCP's
{ content: [{ type: 'text', text: JSON.stringify(...) }] }format. - Zod schemas define tool input shapes;
.shapeis passed toserver.tool()for MCP registration.
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.
- 2mo ago First seen · 58 lines · 659 tokens per session scan A 71ecfd7a35cf
swagger-mcp CLAUDE.md is an instructions file published in the GitHub repository yunhwane/swagger-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 659 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 2026-08-31.
swagger-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swagger-mcp CLAUDE.mdyunhwane/swagger-mcp | Instructions file | 0 | 5mo ago | MIT | A | 659 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |