Skip to main content
An AI agent on its own knows only what is in the current conversation. Connected to Hyperspell, it can look up how your company actually works: who owns a project, what was decided last quarter, what a customer said on the last call, which document is the current version. It gets that context the same way a new colleague would, by asking the brain. You connect agents in the dashboard under Settings, in the Connect Agents section. No code is required for any of the options below.

​
Two ways to get context

Agents reach the brain in two ways, and many use both. The first is to ask questions while working. Hyperspell runs a server that speaks the Model Context Protocol, or MCP, the standard that Claude, ChatGPT, Cursor, and most other agents use to call external tools. Once connected, the agent can search the brain, ask it a question and get a cited answer, or write a note into it, all in the middle of a conversation. This works from any device and needs nothing installed. The second is to read the brain as files. Hyperspell compiles pages about your projects, people, and decisions, and the command line tool keeps a Markdown copy of those pages on your computer. Coding agents such as Claude Code and Cursor read them with the tools they already have, without a network call. This is fast, works offline, and fits how coding agents like to work.

​
What a connected agent can do

The MCP server exposes a small set of tools. The agent picks the right one based on what you ask. Most of the time you do not call these yourself. You ask Claude “what did we decide about the pricing page last month?” and it calls ask. You tell Cursor “check how the billing service handles refunds before you change it” and it reads the relevant page.

​
Agents act as you

Every agent you connect acts with your identity and your permissions. It sees the documents you can see: everything shared with the organization plus your own personal data. It cannot reach a colleague’s private inbox any more than you can. See Permissions for the model behind this. Admins can also create organization-wide API keys for agents that are not tied to a person, such as an internal bot. Those see only content shared with everyone. Configuration covers when to use which.

​
Choose your setup

Claude

Claude on the web, Claude Desktop, and Cowork. One-click connector, sign in with your Hyperspell account.

ChatGPT

ChatGPT on the web and desktop, as a custom connector.

MCP clients

Claude Code, Codex, Cursor, and any other agent that supports MCP.

Command line tool

Keep a Markdown copy of the brain on your machine for coding agents, and ask questions from the terminal.
Slack. If your organization uses Slack, an admin can also install the Hyperspell assistant in your workspace. Mention it in a channel or send it a direct message to ask the brain a question without leaving Slack. It appears as an option in Connect Agents once your Slack integration is connected. This is separate from the Slack integration that indexes your messages.

​
Tips for getting good answers

  • Ask the way you would ask a colleague. “Who is the point of contact at Acme?” works better than a keyword list.
  • Mention names and dates when you have them. The brain resolves people, projects, and time ranges, so “what did Ben say about the migration in June” narrows things down a lot.
  • Ask for sources when it matters. Answers cite the documents they came from, and you can open any of them in the dashboard.
  • If an agent seems to ignore the brain, check that the connector is enabled for the current chat. Claude and ChatGPT both let you turn connectors on and off per conversation.