What you can do with Docs MCP
Create docs and tables from any tool
Ask your favorite AI to draft a brief or create a table, and it appears directly in Docs—no copy-pasting required. Iterate with prompts or jump in and edit it yourself until you’re ready to share.
Let agents handle busywork
Your agents can create tables, update trackers, and document meetings while you focus on doing what only you can.
Search across your docs
No more digging through pages or hunting down updates. Describe what you’re looking for and AI finds it for you, even when you forget the exact name.
Get everyone on the same page
When everything connects, your whole tech stack starts working together, and your team does too. Docs ties every tool your team uses to the same shared context so everything stays in sync.
Your AI gets smarter. You stay in control.
Your permissions, enforced
The MCP only accesses what your existing Docs permissions and seat allow.
Decide who connects
Decide who can use the MCP and the connection method.
Manage type of access
Read only, write only, and more granular controls coming soon.
Frequently asked questions
MCP (Model Context Protocol) is an open standard that lets AI tools work directly inside your other tools. Superhuman Docs runs an MCP server built on this standard so when you connect an AI like Claude or ChatGPT, it gains the ability to read, analyze, and update your docs on your behalf. Instead of working in Superhuman Docs, you can prompt in the chat window of your chosen AI tool, and the AI carries it out directly in your doc.
MCP is included on all paid plans. While rate limits do apply, they are high and should not interfere with reasonable MCP usage. Free plan users can try it out with read-only access for up to 30 requests per week (with a max of 60 requests per month).
You can find all our available MCP connectors and setup instructions in our help center.
You can learn more about Docs MCP in our help center.
AI has a collaboration problem. Docs solves it.
Align quickly and save your team from constant context-switching with one surface where teams, data, and AI connect to get work done.