Team chat apps with AI agents and MCP in 2026
How to judge AI support in team chat: MCP, bots, summaries and which tools you can connect.
The short answer
AI in team chat now means more than a summary button. Look for four things: summaries of threads and meetings, bots and webhooks, an MCP server so outside agents can use your workspace, and integrations with the tools your agents need such as docs and code hosts.
A checklist
Summaries
Thread summaries and meeting minutes with to-dos.
Bots and API
Automation without a vendor app.
MCP
Standard access for Claude Code, Codex, Cursor and others.
Connections
Notion pages and GitHub repos as context.
Control
Tokens, bot accounts and what each can see.
What makes Dock different: it connects to your tools
Dock connects the places your team already works. Notion: connect your Notion pages, then type @notionpage_ in any chat to tag a page; everyone gets a preview card and your AI agents can read it. GitHub: link GitHub read-only, pin repositories to a chat, tag them with @github_ and ask the AI about them. Claude and Codex: use your own Claude or Codex plan inside Dock chats, or connect any MCP agent to your workspace with a token.
All of this sits next to chat, video meetings (with recording, transcripts and AI summaries), docs, tables, calendar, tasks and a drive, in a self-hosted app with no per-seat licence. You run the server yourself, and some integrations are young, so check the setup guides for what each one covers.
Be realistic
Agents misread context. Keep a human in the loop for anything posted in busy channels, give unattended agents their own bot account with narrow access, and test summaries before you rely on them.
Questions
Which team chat apps support MCP?
Support is growing. Check each vendor's docs. Dock includes an MCP server.
Is AI in chat safe?
As safe as the access you give it. Limit tokens and review output.