Enables AI agents to securely read from and interact with Matrix and Microsoft Teams chat under scoped, expiring, human-approved grants, with per-operation approval for sending and editing messages and no free access to room content.
Connects MCP clients such as ChatGPT and Claude to a user's Feishu tenant through OAuth, offering 91 read and write tools covering documents, wiki nodes, spreadsheets, Base records, calendar events, tasks, chats, and cloud files. Per-user authorization, isolated read/write scopes, and token rotation keep actions scoped to the consenting account.
Enables AI agents to send and update Feishu/Lark messages, cards, files, and images, read recent chat context and block on human replies, and work with bitables, spreadsheets, and cloud docs through 25 tools. Runs over long connection or HTTP callbacks, so no public IP is needed.
Enables agents to treat Feishu conversations as an operating interface by sending real files, reading conversation context, pausing for human approval, and refreshing progress cards in place through 25 tools, without requiring a public IP.