A command for checking or manually starting authentication for the Mercado Pago MCP server. Mercado Pago is a payment platform, and MCP is a way for Claude Code to connect to external tools.

Use it to verify the Mercado Pago connection or start authentication when the connection is broken. It does not configure seller OAuth for an application’s marketplace payments.

It helps determine whether Claude Code can actually reach Mercado Pago when a payment-related connection is unavailable or needs checking.

mp-connect — Command for Claude Code by mercadopago

Install

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.

Clone the repo

git clone --depth 1 https://github.com/mercadopago/mercadopago-claude-marketplace

Made for: Claude Code.

Or install mercadopago, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 1 agent, 2 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/mercadopago/mercadopago-claude-marketplace/mp-connect/github.svg)](https://agentmods.dev/commands/mercadopago/mercadopago-claude-marketplace/mp-connect)

Your own site

<a href="https://agentmods.dev/commands/mercadopago/mercadopago-claude-marketplace/mp-connect"><img src="https://agentmods.dev/badge/commands/mercadopago/mercadopago-claude-marketplace/mp-connect/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/mercadopago/mercadopago-claude-marketplace/mp-connect"><img src="https://agentmods.dev/badge/commands/mercadopago/mercadopago-claude-marketplace/mp-connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,213 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00008	$0.01213
Opus 5	$0.00004	$0.00607
Sonnet 5	$0.00002	$0.00243
Haiku 4.5	$0.00001	$0.00121

Measured 12d ago against content hash 1fca6d9e31a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mp-connect 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.

plugins/mercadopago/commands/mp-connect.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mp-connect

The Mercado Pago MCP server is registered automatically when the plugin loads. Authentication is triggered by Claude Code the first time the MCP is used — no manual setup needed.

Use this command only if the connection is broken or you want to verify the status.

Note: Mercado Pago also supports seller OAuth for marketplace payment flows. This command authenticates Claude Code with the Mercado Pago MCP server; it does not configure the seller OAuth flow used by an application. For marketplace integrations, use /mp-integrate product=marketplace.

Step 1 — Check status

The plugin bundles its MCP configuration and Claude Code registers it automatically. Never copy the plugin's .mcp.json into the developer's project and never search an installation cache manually.

ListMcpResourcesTool always returns "No resources found" for this MCP and is not a reliable check. The bootstrap tools authenticate / complete_authentication always exist and prove nothing.

Verify by attempting to call mcp__plugin_mercadopago_mcp__application_list:

The tool is callable AND returns a real application payload (with site_id, etc.) → tell the user: "✓ Connected and ready." and stop.
The tool is not in your capabilities, or it returns an auth error → do NOT ask the user to run /mcp. Continue to Step 2.

Step 2 — Start OAuth directly

Call mcp__plugin_mercadopago_mcp__authenticate. Show the returned URL as a clickable link and render the following message in the developer's language — always, every time:

🔗 Connect Mercado Pago

⚠️ Cmd+Click the link above (Mac) or Ctrl+Click (Windows/Linux). Do not copy and paste the URL into an external browser. Its localhost redirect works only when Claude Code intercepts the click.

When you see "Authentication Successful", return here and let me know.

When the user responds:

Call application_list directly. If the browser showed "Authentication Successful", the local MCP server already processed the callback and the token is live.
Do NOT call complete_authentication first — it will hang trying to reach a socket that was already closed.
Only if application_list fails AND the browser showed an error (not "Authentication Successful") → call complete_authentication. ⚠️ Do not ask the user to paste the callback URL — it contains a sensitive OAuth code. Ask them to re-run the flow (/mp-connect) instead.

Read the full file on GitHub · 108 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.

12d ago First seen · 108 lines · 8 tokens per session scan A 1fca6d9e31a1

Subscribe to this mod's changes

mp-connect is a command published in the GitHub repository mercadopago/mercadopago-claude-marketplace (26 stars, last pushed 8d ago), licensed Apache-2.0. It adds 8 tokens to every session and 1,213 once invoked, about $0.0000 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.

mp-connect

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/mp-connect

Step 1 — Check status

Step 2 — Start OAuth directly

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze