Discord

List Discord bot connections linked to this install — id, label, default guild_id.

Return the bot's own user profile (id, username, discriminator, avatar, etc).

List the servers (guilds) the bot is a member of.

Get one guild's metadata. Falls back to the connection's default guild_id. Bulk support: accepts guild_ids for batched execution.

List channels in a guild. Falls back to the connection's default guild_id. Bulk support: accepts guild_ids for batched execution.

List members of a guild. Requires the bot to have the Server Members intent enabled in the developer portal — may return 403 otherwise. Bulk support: accepts guild_ids for batched execution.

Get a channel's metadata (type, name, topic, parent, permissions). Bulk support: accepts channel_ids for batched execution.

Read recent messages from a channel (newest first). Pagination via `before` / `after` / `around` (message ids). Requires Message Content intent for non-bot message bodies in some cases. Bulk support: accepts channel_ids for batched execution.

Fetch a single message by id. Bulk support: accepts channel_ids, message_ids for batched execution.

Public profile of any Discord user by id. Bulk support: accepts user_ids for batched execution.

Post a message to a channel. Provide `content` (text up to 2000 chars), `embeds` (rich JSON), or both. `reply_to` makes it a reply. Bulk support: accepts channel_ids for batched execution.

Open a DM channel with a user and send them a message. The bot and the user must share a guild. Bulk support: accepts user_ids for batched execution.

Edit a previously-sent message (must be authored by this bot). Bulk support: accepts channel_ids, message_ids for batched execution.

Add a reaction to a message. `emoji` is either unicode (e.g. `👍`) or `name:id` for custom guild emoji. Bulk support: accepts channel_ids, message_ids for batched execution.

Delete a message. Irreversible. Bot needs Manage Messages to delete messages authored by other users. Bulk support: accepts channel_ids, message_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.