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.
npx agentmods add instructions/sumup/sumup-mcp/agents-mdgit clone --depth 1 https://github.com/sumup/sumup-mcpWhat 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 | $0.00471 | $0.00471 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
sumup-mcp AGENTS.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 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.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository guide for coding agents working in @sumup/mcp.
Purpose
- This repository implements a SumUp MCP server as a Cloudflare Worker.
- It uses Hono for routing, a Durable Object-backed
McpAgentfor session handling, and OAuth bearer JWT validation against SumUp auth JWKS. - Key files:
src/worker.ts,src/app.ts,src/auth.ts,src/protocol.ts,src/sumup-agent.ts.
Environment and Runtime
- Package manager:
npm. - Required runtime: Node.js
>=22. - Module system: ESM (
"type": "module"). - TypeScript is configured with
strict: trueandmoduleResolution: "bundler". - Local dev and deployment use Cloudflare Wrangler.
- Worker configuration is in
wrangler.jsonc. - Durable Object binding name:
SUMUP_MCP_AGENT.
Install and Setup
- Install dependencies:
npm install - Start local worker dev server:
npm run dev - Generate Cloudflare worker types if needed:
npm run generate-types
Build, Lint, Typecheck, and Test
- Build/typecheck:
npm run build - Explicit typecheck:
npm run typecheck - Lint and format check:
npm run lint - Auto-fix lint/format issues:
npm run lint:fix - Run tests:
npm run test
Change Management Guidance for Agents
- Prefer minimal targeted edits; this is a small, focused codebase.
- Do not introduce new dependencies without a clear reason.
- Keep OAuth, MCP, and protocol terminology accurate.
- If changing public behavior, update or add tests in the same change.
- If a change affects contributor workflow, update
CONTRIBUTING.mdor this file as needed.
PR and Commit Guidance
- Follow Conventional Commits for PR titles and keep PR summaries explicit about behavior changes.
References
- See Model Context Protocol (MCP) specification at https://modelcontextprotocol.io/specification/latest
- Strictly follow the MCP Authorization guidelines at https://modelcontextprotocol.io/specification/latest/basic/authorization
- Refer to OAuth 2.0 RFCs and standards for further information
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.
- 2d ago First seen · 52 lines · 471 tokens per session scan A e1b7725f0de1
sumup-mcp AGENTS.md is an instructions file published in the GitHub repository sumup/sumup-mcp (7 stars, last pushed 8d ago), licensed Apache-2.0. It adds 471 tokens to every session, about $0.0024 per session on Opus 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.
Other instructions, from other repositories
sumup-skills GEMINI.md
Instructions for sumup/sumup-skills: This extension provides guidance for building SumUp payment integrations.
PySentinel-Pain001-Enterprise
Enterprise-grade Release Architect. Enforces 95%+ coverage, security-hardened XML, resilient release orchestration, and zero-trust quality model.
x402trace CLAUDE.md
Instructions for fardinvahdat/x402trace, covering claude.md — operating manual for x402trace, project mission, status, hard rules — non-negotiable and strict audit gate (autonomous mode).
agent-wallet-sdk AGENTS.md
Instructions for up2itnow0822/agent-wallet-sdk, covering agents.md -- agent wallet sdk, purpose, ownership, local contracts and work guidance.
piprail CLAUDE.md
Instructions for piprail/piprail, covering piprail — project guide, what this is, architecture (this is the whole product), repo layout and conventions (on top of the global guide).
piprail AGENTS.md
Instructions for piprail/piprail, covering agents.md, commands, project structure, api ground truth (get these right) and always.