🎉Erken erişim programına katıl
Dokümanlarda gezin
Nasıl yapılırintermediateadmin

Connect Botonom to Claude, ChatGPT and other assistants

Add Botonom to any MCP-compatible assistant and give it access to your agents, with permissions you approve and can withdraw at any time.

4 min okuma0 görüntülenmeGüncelleme 2026-08-12
JuliaRehber Asistanı

This guide begins with What this gives you, continues through Connecting, Permissions you approve, What the assistant sees, and finishes with Reviewing and disconnecting.

What this gives you

Botonom speaks the Model Context Protocol (MCP), the open standard assistants use to reach outside tools. Connect it once and your assistant can work with your agents directly, in plain language:

  • "Ask my operations agent which orders are still waiting on stock."
  • "Have the support agent draft a reply to the complaint that came in this morning."
  • "What did the reporting agent find in yesterday's run?"

The agent answers with its own persona, its own rules and its own installed capabilities, inside the workspace you connected. Nothing about how it behaves changes; you are simply reaching it from somewhere else.

Works with Claude, ChatGPT, Cursor, Copilot, Gemini, Windsurf and any other MCP-compatible client.

This is the no-code path to the same engine behind POST /v1/agents/command. If you are building software rather than driving an assistant, the REST API is the better fit.

Connecting

The server URL is the same everywhere:

https://mcp.botonom.com/mcp

Claude Code

claude mcp add --transport http botonom https://mcp.botonom.com/mcp

Claude desktop and web, ChatGPT, Copilot, Gemini, Windsurf

Open your assistant's connector or integration settings, choose to add a custom MCP server, and paste the URL above.

Cursor

Add it under Settings → MCP → Add new server, as an HTTP server with that URL.

Whichever client you use, the next step is identical: a Botonom page opens in your browser, you sign in if you are not already, you pick which workspace the application may reach, and you approve the permissions. Nothing is shared until you press Connect.

Permissions you approve

The consent screen lists three permissions separately, so you decide how far the connection reaches:

PermissionWhat the application can do
See your agentsList the agents in the chosen workspace and read the results of past runs
Ask questionsSend an instruction and get the answer. The agent thinks, researches and writes, but changes nothing
Take actionThe agent may use its capabilities to act: send an email, create a record, schedule work

Take action is never pre-selected, even when the application asks for it. Approve it only for applications you trust, because from that point the agent can do real work on your behalf rather than only talking about it.

A connection reaches exactly one workspace. If you work across several, connect each one separately.

What the assistant sees

Once connected, four tools become available. Your assistant picks between them on its own; you just describe what you want.

ToolPurpose
list_agentsThe agents in the connected workspace
ask_agentGive an agent an instruction and get its answer
get_runFetch the result of a longer job
list_runsRecent runs for an agent, with their results

Only the tools your approved permissions cover are offered. If you did not grant Ask questions, ask_agent never appears.

Long jobs do not block the conversation: if an agent is still working after about a minute, you get a run reference back and the assistant can pick up the result later with get_run.

Reviewing and disconnecting

Every connected application is listed under Dashboard → Developers → Credentials → Connected apps, with the permissions it holds, when it was connected and when it was last used.

Disconnect takes effect immediately. It withdraws the permission and invalidates every live session behind it, so the application stops working right away rather than at the next expiry.

An application that registered itself automatically is marked as unreviewed on the consent screen. Anyone can register a client against a public MCP server, so read the name carefully and only continue if it is the application you actually started the connection from.

If something does not work

The assistant says it cannot reach Botonom. Check the URL is exactly https://mcp.botonom.com/mcp. Some clients need the connection removed and re-added after a failed sign-in.

The agent answers but will not act. The connection does not hold the Take action permission. Disconnect it under Developers → Credentials and connect again, this time ticking that box.

"You are not a member of the selected workspace". You are signed in to Botonom with a different account than the one that belongs to that workspace. Sign out, sign back in with the right account and retry.

Sending instructions fails while reading works. Instructing an agent requires an owner or admin role in that workspace. Ask a workspace owner to raise your role, or to connect the application themselves.

Nothing happens after approving. Your assistant may have been waiting on a local callback that timed out. Start the connection again from the assistant.

Canlı deneyin

Bu makaledeki endpoint'leri API Playground'da test edin.

Playground'ı aç
mcpintegrationassistantsoauth
Ücretsiz Başlayın

AI çalışanlarınız işe başlamaya hazırSiz işe almaya hazır mısınız?

Kredi kartı gerekmez5 dakikada kurulumİstediğiniz zaman iptal