mp-test-setup
Create test users and add funds to them for Mercado Pago testing. Wraps create_test_user and add_money_test_user from the MCP. Clarifies that all credentials (including test users) use the APP_USR- prefix — there is no longer a TEST- sandbox.
What this skill does
# mp-test-setup
This skill is the only place test users get created. It exists because the testing model is a frequent source of confusion (legacy docs still mention `TEST-` credentials that no longer exist).
---
## The current testing model — read first
- **There is no separate sandbox.** Tests run against the production API using the credentials of a **test user**.
- **Test user credentials use the `APP_USR-` prefix**, exactly like real production credentials. There is no way to tell them apart by prefix.
- The legacy `TEST-` prefix is **deprecated**. Never suggest it, never ask if a credential is "sandbox" by its prefix.
- A test user has its own balance (loaded via this skill) and behaves like any real account.
- For automated test credentials without creating a test user: in the Developer Dashboard, *Tus integraciones → Datos de integración → Credenciales* → click **"Prueba"** (Brazilian Portuguese: *Suas integrações → Dados de integração → Credenciais → "Teste"*).
---
## Step 0 — Verify MCP is actually authenticated
`ListMcpResourcesTool` is unreliable for this MCP (always returns "No resources found"). The bootstrap tools `authenticate` / `complete_authentication` are always present and prove nothing.
Check whether `mcp__plugin_mercadopago_mcp__application_list` is callable AND returns at least one application. If not, stop and tell the user:
> Call `mcp__plugin_mercadopago_mcp__authenticate`, show the URL as a clickable link, and say: "When you see **Authentication Successful** in the browser, come back and say anything." When the user responds, call `application_list` directly — do NOT call `complete_authentication` first (it hangs when the callback was already consumed). Never ask the user to paste the callback URL — it contains a sensitive OAuth code.
---
## Step 1 — Resolve `site_id` before asking
The MCP does not currently return a `site_id` (its `application_list` only returns `AppID`/`AppName`/`AppDescription`, and the OAuth access token that would let us call `/users/me` is not exposed to the plugin client). Resolve in this order:
1. **Use the country the agent already passed** as `country=` — the agent already resolved it (persisted state or wizard).
2. **Read `.mp-integrate-progress.md`** at the project root — if a previous run persisted a country, reuse it.
3. **Last resort**: ask via `AskUserQuestion` (picker, never a numbered text block). Persist the answer to `.mp-integrate-progress.md`.
Do **not** grep the repo for `currency_id`/`site_id` literals or locale strings — they're unreliable on a clean repo and waste tokens.
## Step 2 — Create a test user
Call `mcp__plugin_mercadopago_mcp__create_test_user` with:
| Param | Required | Values |
|-------|----------|--------|
| `site_id` | yes | `MLA` (Argentina), `MLB` (Brazil), `MLM` (Mexico), `MLC` (Chile), `MCO` (Colombia), `MPE` (Peru), `MLU` (Uruguay) |
| `description` | yes | Free text identifying the user (e.g., `"buyer for checkout-pro tests"`) |
| `profile` | yes | `seller` or `buyer` — pick the role you need to simulate |
| `amount` | optional | Initial balance in the country's currency |
The tool returns the user id, email, password, and `APP_USR-` credentials. Show them to the developer with a reminder: **these are not committable secrets — load them from `.env` only**.
> If the developer needs both sides of a transaction (typical for marketplace, subscriptions, P2P), create one `seller` and one `buyer`.
---
## Step 3 — Load funds (when needed)
Call `mcp__plugin_mercadopago_mcp__add_money_test_user` with:
| Param | Required |
|-------|----------|
| `test_user_id` | yes — the id returned by `create_test_user` |
| `amount` | yes — number in the user's currency |
Country-specific limits apply. If the call fails with a limit error, ask for a smaller amount and retry once.
---
## Step 4 — Test cards
For card testing, do **not** invent card numbers. Query MCP `search_documentation` with `"test cards {country}"` (e.g., `"test cards argentina"`) — the official set changes per country and per acquirer.
---
## Step 5 — Hand the credentials to the developer
Output template:
```markdown
## Test user created
**Country**: {country}
**Profile**: {seller | buyer}
**User id**: {id}
**Email**: {email}
**Initial balance**: {amount} {currency}
### Credentials (load from `.env`, never commit)
```
MP_ACCESS_TOKEN=APP_USR-...
MP_PUBLIC_KEY=APP_USR-...
```
### Next steps
- Smoke test with `mp-webhooks` → `simulate_webhook`.
- Run `mp-review` to validate the integration once a payment goes through.
- For card payments, query MCP for current test cards: `search_documentation("test cards {country}")`.
```
---
## Gotchas
- Test user credentials look identical to production credentials. If a `.env` file leaks, both buyer and seller balances are exposed.
- The test user's email/password are valid logins on `mercadopago.com.{tld}` — the developer can sign in to inspect movements.
- A test user belongs to the country specified by `site_id`; trying to use Argentine test credentials against the Brazilian site fails silently with a `not_found` payment.
- Adding money has per-country daily limits. If you hit them, create a fresh test user instead of bumping limits.
---
## What this skill does NOT do
- It does **not** issue real production credentials. Those come from the Developer Dashboard.
- It does **not** validate webhooks (use `mp-webhooks`) or scaffold integration code (use `mp-integrate`).
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.