mcpbeat

iFood MCP Server

io.github.mcp-dir/ifood-mcp
answering

iFood is answering right now. Last checked 8 min ago. It exposes 22 tools. Last commit 12 Jun 2026.

Insights for your iFood store right in your AI assistant's chat. Generate charts of sales and payout

Uptime history 42 hours of history · worst hour 50%
42 hours agonow
95.6%
Uptime 24h
87 of 91 checks
22
Tools
read from the server
590 ms
Response time
average over 24h
1
Stars
last commit 12 Jun 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

run in your terminal
claude mcp add ifood-mcp --transport http https://api.mcp.ai/p_ifood
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "ifood-mcp": {
      "url": "https://api.mcp.ai/p_ifood"
    }
  }
}
~/.codex/config.toml
[mcp_servers.ifood-mcp]
url = "https://api.mcp.ai/p_ifood"
.cursor/mcp.json
{
  "mcpServers": {
    "ifood-mcp": {
      "url": "https://api.mcp.ai/p_ifood"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "ifood-mcp": {
      "url": "https://api.mcp.ai/p_ifood"
    }
  }
}

Available tools 22

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

ifood
ifood_catalog_summary
Resumo do cardápio (chart-ready): totais (catálogos, categorias, itens, disponíveis/indisponíveis), faixa de preço (min/médio/máx) e mix por categoria (by_category). Ideal pra gráfico de composição de cardápio. Bulk support: accepts merchant_ids for batched execution.
ifood_financial_summary
Resumo financeiro agregado do período (chart-ready): total de pedidos, faturamento bruto, ticket médio, série diária (by_day), por forma de pagamento (by_payment_method) e repasses. Ideal pra gráficos de vendas no tempo. Datas YYYY-MM-DD; default = últimos 30 dias. As vendas são buscadas em janelas de até 8 dias automaticamente.
ifood_get_merchant
Detalhe da loja: nome, razão social, endereço, ticket médio, tipo, status, canais. Bulk support: accepts merchant_ids for batched execution.
ifood_get_opening_hours
Horários de funcionamento da loja (shifts por dia: dayOfWeek, start, duration em minutos). Bulk support: accepts merchant_ids for batched execution.
ifood_get_reconciliation
Conciliação financeira de uma competência (YYYY-MM): links dos arquivos detalhados (CSV) com o financeiro completo por pedido.
ifood_get_status
Status operacional da loja em tempo real (aberta/fechada, available, motivos). Bulk support: accepts merchant_ids for batched execution.
ifood_list_accounts
Lista as lojas iFood (conexões) vinculadas a este install — merchant_id, label.
ifood_list_anticipations
Antecipações de recebíveis no período (se a loja contratou antecipação no iFood). Datas YYYY-MM-DD (data de cálculo).
ifood_list_catalogs
Lista os catálogos (cardápios) da loja — catalogId, groupId, status. Bulk support: accepts merchant_ids for batched execution.
ifood_list_categories
Categorias de um catálogo (com itens por padrão): id, nome, status, itens (nome, preço, disponibilidade). Bulk support: accepts merchant_ids, catalog_ids for batched execution.
ifood_list_interruptions
Lista as pausas (interruptions) ativas/agendadas da loja. Bulk support: accepts merchant_ids for batched execution.
ifood_list_merchants
Lista as lojas visíveis à conexão (id, nome, razão social). Paginação opcional (page, size — máx 10).
ifood_list_reviews
Lista avaliações individuais (nota, comentário, data) paginadas — pra histograma de notas ou ler comentários recentes. Bulk support: accepts merchant_ids for batched execution.
ifood_list_sales
Lista crua de vendas/pedidos do período (forma de pagamento, valores, taxas) pra análise detalhada. ATENÇÃO: a janela máxima da API é 8 dias (ajustada automaticamente). Pra períodos longos use ifood_financial_summary.
ifood_list_settlements
Repasses (settlements) recebidos no período — valor líquido transferido, saldo. Datas YYYY-MM-DD (por data de pagamento).
ifood_reviews_summary
Resumo das avaliações da loja: nota agregada (score) e contagem total/válidas. Ideal pra indicador de satisfação. Bulk support: accepts merchant_ids for batched execution.
authenticate
authenticate
MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.
connect
connect
Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
marketplace
marketplace
The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin.
report
report_bug
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
show
show_version
Show the current MCP platform and adapter versions.
toolkit
toolkit_info
Returns the current toolkit state: installed MCPs, their connection status, and how many catalog tools each exposes.

Endpoints

URLTransportStateLatencyChecked
https://api.mcp.ai/p_ifood streamable-http answering 193 ms 8 min ago

iFood — questions

Answers built from our own checks of this server.

What can iFood do?
It exposes 22 tools, read directly from the server on our last check. Among them: authenticate, connect, ifood_catalog_summary, ifood_financial_summary, ifood_get_merchant, ifood_get_opening_hours and 16 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is iFood working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 87 of 91 checks got a reply (95.6%), average response time 590 ms. The bar chart above shows every period we have measured.
How do I connect iFood?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does iFood need an API key?
No. iFood completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 22 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is iFood?
It answers our handshake in 590 ms on average, which is faster than 17% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is iFood open source?
Yes — it is published under the MIT licence and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.