Poupa AI MCP server

• authenticateFree

  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.

• connectFree

  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.

• marketplaceFree

  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. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

• poupa_add_transactionFree

  Cria uma transação. value e date são obrigatórios; demais campos opcionais. Para parcelar, use installments; para recorrer, use expense_recurrency (dias) OU recurrency_array_dates (lista de datas).

• poupa_add_transactionsFree

  Cria várias transações de uma vez (bulk). transactions[] é obrigatório; cada item segue o mesmo shape de poupa_add_transaction.

• poupa_banksFree

  Lista os bancos/contas do usuário.

• poupa_cardsFree

  Lista os cartões de crédito do usuário.

• poupa_categoryFree

  Lista as categorias do usuário.

• poupa_defaultsFree

  Categorias e métodos de pagamento padrão do usuário.

• poupa_delete_transactions_by_filterwrite actionFree

  Deleta transações por filtro. O filtro precisa ser não vazio (a tool se recusa a deletar tudo). Aceita ids, intervalo de datas, descrição, categoria, etc.

• poupa_get_balanceFree

  Saldo do usuário, agrupado por banco, categoria, método de pagamento, cartão, tipo (entrada/saída) e mês. start_date/end_date (YYYY-MM-DD) limitam a janela; sem datas, traz tudo.

• poupa_memoriesFree

  Memórias/notas do usuário gravadas no Poupa AI.

• poupa_preferencesFree

  Preferências do usuário (idioma, moeda, etc.).

• poupa_retrieve_transactionsFree

  Lista transações no intervalo (YYYY-MM-DD), opcionalmente filtradas por palavras-chave (match parcial case-insensitive na descrição), cartão e/ou banco/pagador.

• poupa_transfer_between_bankswrite actionFree

  Registra uma transferência entre dois bancos/contas do PRÓPRIO usuário (movimento contábil — não executa transferência bancária real). value é o valor; date opcional (default = hoje).

• poupa_update_transactionswrite actionFree

  Atualiza uma ou mais transações existentes. Informe os ids alvo no filtro e os campos a alterar (passthrough).

• report_bugFree

  Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

• show_versionFree

  Show the current MCP platform and adapter versions.

• toolkit_infoFree

  Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 949ms20/20
• Tool poisoning19 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 3 write-action tools with no auth3/15
• Maintenancelast push 63 days ago12/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Safety score

79/100

higher than 63% of 1,761 Finance servers

Tools

19

the typical Finance server has 8

Tools that change things

16%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote Finance server answers 100%

Response time

215 ms

faster than 63% of 1,133 Finance servers

Poupa AI: common questions

Is Poupa AI MCP server safe?

Mostly: it is graded B (79/100). Read the Poupa AI safety report

How do I install Poupa AI?

It runs remotely at api.mcp.ai. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Poupa AI need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Poupa AI maintained?

The last commit was 66 days ago (2026-08-30). The latest release is v0.1.0.

Is Poupa AI up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of Poupa AI?

Servers from other publishers that do the same job: MoneyMatter MCP server, Pluggy MCP server and T-Bank MCP server.

How does Poupa AI compare with other Finance MCP servers?

safety score 79/100 (higher than 63% of 1,761 Finance servers); tools 19 (the typical Finance server has 8); tools that change things 16% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.