Mercado Livre Vendedor

Lista as contas Mercado Livre conectadas a este install — id, label, seller_id.

Dados da conta do vendedor conectado (GET /users/me): perfil, reputação, site, tipo de conta, status de vendedor.

Detalha um usuário público por id (GET /users/{id}). Bulk support: accepts ids for batched execution.

Lista os ids dos anúncios do vendedor conectado (GET /users/{seller}/items/search). Paginado (offset/limit). Filtro opcional `status` (active, paused, closed). Retorna ids + paging; use mercadolivre_get_items pra detalhar.

Detalha um ou mais anúncios por id (GET /items?ids=). Informe `ids` (lista, máx 20). Filtro opcional `attributes` (campos a retornar, separados por vírgula).

Busca anúncios do vendedor já com detalhes (GET /sites/{site}/search?seller_id=). Paginado. `site` default MLB (Brasil). Filtro opcional `q` (texto), `category`.

Lista pedidos do vendedor conectado (GET /orders/search?seller=). Paginado. Filtros opcionais: `order.status` (paid, confirmed, cancelled...), `sort` (date_asc/date_desc), `q` (busca).

Detalha um pedido por id (GET /orders/{id}): itens, comprador, pagamento, envio. Bulk support: accepts ids for batched execution.

Lista perguntas recebidas pelo vendedor (GET /questions/search?seller_id=). Paginado. Filtros opcionais: `status` (UNANSWERED, ANSWERED), `item` (id do anúncio).

Detalha uma pergunta por id (GET /questions/{id}). Bulk support: accepts ids for batched execution.

Detalha um envio por id (GET /shipments/{id}): status, rastreio, endereço, custo. Pegue o shipping.id no detalhe do pedido (mercadolivre_get_order). Bulk support: accepts ids for batched execution.

Lista as categorias raiz de um site (GET /sites/{site}/categories). `site` default MLB.

Detalha uma categoria por id (GET /categories/{id}): caminho, atributos, settings. Bulk support: accepts ids for batched execution.

Visitas de um anúncio numa janela de tempo (GET /items/{id}/visits/time_window). Informe `last` (quantidade) e `unit` (day, week, month). Bulk support: accepts ids for batched execution.

Show the current MCP platform and adapter versions.

無需輸入參數。

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

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.

無需輸入參數。

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

無需輸入參數。

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.

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.