Any tool that can add an MCP server or connector: Claude, ChatGPT, code editors such as Cursor and VS Code, and agents you build. It's on every plan, with a number of agent connections per person.

Can an agent read my DMs?

Only if admins turn on Let agents read private channels and direct messages, and then only the private conversations of the person who connected it. It's off by default.

Can an agent pretend to be me?

No. Everything it posts is marked as its own, with an AI agent badge and who it's for. Agents treat what they read in messages as information, never as instructions.

Can admins see what agents did?

Yes. The AI agents page shows who connected or disconnected what, approvals and blocks, and every tool call with whether it worked, for 90 days.

AI agents

Bring your own agent. It works as itself, with only what you allow.

Freesbe's AI agents are the AI tools people already use, connected over the open Model Context Protocol: Claude, ChatGPT, a code editor, or an agent your team built. An agent reads what you can read, posts as its own bot with an AI agent badge, and asks teammates questions for you. Admins approve, limit or block each one.

Start free Book a demo See pricing

Connect Claude to Freesbe: pick a workspace, see what it will be able to do, and allow it

Connect in a minute, no app to install

In your AI tool, add Freesbe as a connector or MCP server with one address. Freesbe opens a page in your browser where you sign in as usual, pick the workspace, read what the agent will be able to do and click Allow. Your workspace's sign-in rules apply, including single sign-on and a second step.

Claude: Settings, Connectors, Add custom connector. ChatGPT: Settings, Connectors. Code editors: mcp.json
One connection is for one workspace; connect again for another
Disconnect from your preferences and it stops at once

Preferences, AI agents: Claude and Cursor connected to Northwind Traders

What an agent can do

Search the messages you can see, read a channel or a thread, post in a channel or send a DM, react, find people, check who's around and when they're free, see your meetings and to-dos, read the notes of meetings you were in, and place a phone call through your Freesbe phone. Every message it reads comes with a link back to it, so it can point you to its sources.

A message in #spring-launch posted by Claude, with Sent by Claude, an AI agent, for Maya Chen under it

See it on your own team's data.

Start free with up to 10 people and try it today, or book a 20-minute demo with the people who make Freesbe.

Book a demo Start free

It asks people for you

An agent can ask a teammate something like When will the Acme Corp order ship? and wait for the answer. The question arrives as a DM from the agent, saying who it's asking for, with the right way to answer: a date, choices, yes or no, a number or a few words. It waits for working hours, the person can pass it on, and you hear back in your own DM.

A direct message from Claude asking Maya Chen when the Acme Corp order will ship, with a date picker

Visible, limited, logged

An agent shows in the member list and in messages as its own bot with an AI agent badge and the name of the tool it is, never as the person. Admins choose whether anyone can connect agents, only approved ones, or nobody; set the most each agent may do; keep private channels and DMs off limits; block or remove an agent; and read 90 days of everything agents did.

Workspace settings, AI agents: who can connect, the agents people connected with Approve, Block and Permissions, and the activity log

For developers

Freesbe's MCP server speaks the current MCP specification over streamable HTTP with OAuth 2.1, so a standard MCP client connects with no Freesbe-specific code. Scopes are the permissions people see, by their short names. Access tokens last an hour and refresh for 30 days.

Questions

Which tools work?: Any tool that can add an MCP server or connector: Claude, ChatGPT, code editors such as Cursor and VS Code, and agents you build. It's on every plan, with a number of agent connections per person.
Can an agent read my DMs?: Only if admins turn on Let agents read private channels and direct messages, and then only the private conversations of the person who connected it. It's off by default.
Can an agent pretend to be me?: No. Everything it posts is marked as its own, with an AI agent badge and who it's for. Agents treat what they read in messages as information, never as instructions.
Can admins see what agents did?: Yes. The AI agents page shows who connected or disconnected what, approvals and blocks, and every tool call with whether it worked, for 90 days.

How it works, step by step

The help guide shows every screen and setting. AI agents

See more on this topic

Try all of it free with up to 10 people.

No card, no time limit. Invite your team and see what sticks.

Start free Book a demo