Skip to main content
The Chatbase MCP server lets an AI assistant work directly with your Chatbase workspace. It can list agents, manage the sources an agent is trained on, read conversations, and handle help desk tickets, without you copying data between tools. It is a remote Model Context Protocol server. There is nothing to install or self-host.

Endpoint

https://mcp.chatbase.co/api/mcp

Authentication

OAuth 2.1, with no API key to create or paste
The endpoint is not a page to open in your browser. Add it to an MCP client, and the client opens the sign-in page for you.

​
Claude and ChatGPT

Add Chatbase under Settings → Connectors → Add custom connector, using the endpoint above, then approve access when prompted.
On ChatGPT’s default Allow low-risk actions setting, the tools marked destructive are hidden rather than offered with a confirmation prompt. That covers deleting an agent or a source, and editing a source. If ChatGPT says it cannot delete or edit something, raise the permission setting for the connector.

​
Claude Code, Codex, Cursor and other clients

Point the client at the endpoint. Do not add an Authorization header. The client negotiates OAuth on its own and opens the sign-in page for you.
Then run /mcp and choose Authenticate.

​
How sign-in works

1

Your client registers itself

The first time a client connects, it registers with Chatbase automatically using Dynamic Client Registration. You do not create anything in advance.
2

You approve access in the browser

Chatbase shows a consent screen listing the workspace and exactly which permissions the app is asking for. You choose the workspace and approve or deny.
3

The client receives a token

Access is granted to that one client, for that one workspace, limited to the permissions you approved.
Chatbase never shows an app more than your own role allows. If you cannot delete sources, no app you approve can delete them either, even if it asks.

​
Token lifetime

​
Permissions

Chatbase groups permissions by resource and verb. An app requests a set, and you approve or deny the whole request. Delete permissions are shown on the consent screen but are not selected by default. Approve them only if the app genuinely needs to remove data. A client only sees the tools its permissions cover. A short tool list usually means a narrow approval rather than a missing feature. Ask the assistant to call chatbase_whoami, which reports the workspace and the exact permissions in use.

​
What the assistant can do

The server exposes 26 tools: chatbase_whoami, which every connected app can call to report its own access, plus 25 grouped by area.
List and inspect agents, create and clone them, update configuration, toggle auto-retrain, and send a chat message to an agent.chatbase_list_agents · chatbase_get_agent · chatbase_create_agent · chatbase_clone_agent · chatbase_update_agent · chatbase_update_agent_auto_retrain · chatbase_delete_agent · chatbase_chat
Add, edit and remove the knowledge an agent is trained on. Every change takes effect immediately, with no separate training step.chatbase_list_sources · chatbase_get_source · chatbase_get_sources_summary · chatbase_create_source · chatbase_update_source · chatbase_delete_source
Export conversations for analysis, and update conversation metadata.chatbase_export_conversations · chatbase_update_conversation
Search, read and update tickets, post replies, and inspect teams and statuses.chatbase_list_tickets · chatbase_search_tickets · chatbase_get_ticket · chatbase_create_ticket · chatbase_update_ticket · chatbase_list_ticket_messages · chatbase_create_ticket_message · chatbase_list_ticket_statuses · chatbase_list_helpdesk_teams
Two source operations cannot be undone. Deleting a source purges its knowledge straight away and nothing restores it. Re-creating the source afterwards starts from scratch. Editing a source overwrites its content and retrains it on the spot, so the previous text is gone. Both are marked destructive, so a well-behaved client will ask before running them.

​
Manage connected apps

Every app you approve appears in your workspace under Settings → General → Connected apps, showing what it can access and when it last obtained a token. Select Revoke to cut off access. It takes effect on the app’s very next request, even if its current token has not expired. The app must ask for your approval again before it can reconnect.
An app’s name is chosen by the app itself when it registers, and Chatbase cannot verify it. Treat the name as a label, not as proof of identity, and revoke anything you do not recognise.

​
Troubleshooting

Expected before you sign in. Trigger your client’s authentication step (/mcp in Claude Code, codex mcp login chatbase in Codex) and approve the consent screen.
The approval was narrower than the task requires. Ask the assistant to call chatbase_whoami to see the permissions in use, then revoke the app under Connected apps and reconnect, approving the permissions it needs.If a permission is missing from the consent screen entirely, your own role does not include it. An administrator has to grant it to you first.
Sources train as soon as they are written, but the work runs in the background. A new source reports untrained until it is live, then trained, or failed if it did not land. An edited one reports updated while it re-trains. Ask the assistant to re-read the source rather than assuming the write finished the job.
Streaming is not available over MCP. chatbase_chat always returns the complete response in one message.