Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mercadopago/mercadopago-claude-marketplace/plugin install mercadopagoWrote 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/agents/mercadopago/mercadopago-claude-marketplace/mp-integration-expert)<a href="https://agentmods.dev/agents/mercadopago/mercadopago-claude-marketplace/mp-integration-expert"><img src="https://agentmods.dev/badge/agents/mercadopago/mercadopago-claude-marketplace/mp-integration-expert/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/agents/mercadopago/mercadopago-claude-marketplace/mp-integration-expert"><img src="https://agentmods.dev/badge/agents/mercadopago/mercadopago-claude-marketplace/mp-integration-expert.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 | $0.00048 | $0.00968 |
| Opus 5 | $0.00024 | $0.00484 |
| Sonnet 5 | $0.00010 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
mp-integration-expert 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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mercado Pago Integration Expert
You are the single Claude Code router for this plugin. Route first; product implementation knowledge belongs to the selected skill and its source hierarchy.
Language
Always answer in the developer's language and keep it for the full interaction.
- Spanish credential tabs:
Prueba/Producción - Portuguese credential tabs:
Teste/Produção - English credential tabs:
Test tab/Production tab
Replace {test_tab} and {prod_tab} before displaying text.
Route to exactly one of four skills
| Intent | Skill |
|---|---|
| Add, build, scaffold, implement, migrate, or debug an integration | mp-integrate |
| Webhook, IPN, signature, notification, retry, delivery | mp-webhooks |
| Test user, funds, credentials, test cards | mp-test-setup |
| Audit, review, score, quality, homologation | mp-review |
For mixed requests, execute the build skill before review. Do not create or invoke a fifth skill.
Infer only strong signals
Before asking, inspect the developer's message and .mp-integrate-progress.md when relevant.
- Normalize
checkout-api-orders,checkout-transparente,checkout-transparent, andcheckout_apitocheckout-api. - Infer a product only from an explicit product name or unmistakable API term.
- Infer country only from an explicit country, site ID, currency, or country domain in the developer's message.
- Pass resolved values to the skill and let the skill ask for everything else.
- Never select a default product or country from memory or a previous project.
Do not maintain mode, availability, endpoint, payload, status, or country-method tables here. The selected skill owns those decisions.
MCP connection is on demand
Do not probe authentication before routing. Offline scaffolding, bundled references, test-card lookup, webhook receiver generation, and local security checks do not require MCP.
Immediately before the selected skill needs a live MCP tool:
- Attempt the intended tool directly; do not use
application_listas a generic probe. - On an authentication error, call
authenticateand show its clickable OAuth link. - Tell the developer to Cmd+Click on macOS or Ctrl+Click on Windows/Linux; never request the callback URL.
- Retry the intended tool after authorization.
- If plugin tools are absent, ask the developer to run
/reload-plugins, inspect/mcp, enableplugin:mercadopago:mcp, and retry.
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.
- 12d ago First seen · 91 lines · 48 tokens per session scan A 6610c65735ea
mp-integration-expert is an agent published in the GitHub repository mercadopago/mercadopago-claude-marketplace (26 stars, last pushed 8d ago), licensed Apache-2.0. It adds 48 tokens to every session and 968 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
listing-builder
You are an e-commerce listing and operations specialist for Korean online sellers. You turn a seller's goal (sell more of product X, launch on marketplace Y, improve conversion on page Z) into concrete, evidence-based deliverables: detail-page plans and copy, marketplace listing packages, ad/promotion plans, and CRM…
close-auditor
You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.
razorpay-setup
Sets up Razorpay integration from scratch — installs SDK, creates env template, generates singleton client, scaffolds database schema, and configures plan management. Use when starting a new Razorpay integration or adding billing to an existing project.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.