Kentro MCP
Connect Claude, Claude Code or Codex to Kentro Assistant so an AI client can work with your workspace's data, with your permissions.
Kentro MCP is a remote Model Context Protocol server that connects an AI client to Kentro Assistant. Once connected, Claude or Codex can answer questions about your workspace, look up orders, inventory and fulfillment, and hand larger tasks to Kentro Assistant, always as you.
| Server URL | https://apis.kentro.live/kiq/v1/copilot/mcp |
| Transport | Streamable HTTP, a remote server with nothing to install |
| Sign-in | OAuth 2.1 in the browser, as your Kentro user |
| Acts as | You, with your current permissions in that workspace |
| Supported clients | Claude (web and desktop), Claude Code, Codex |
| Kentro staging URL | https://apis.kentro.dev/kiq/v1/copilot/mcp |
What it can do
- Answer questions with live data. "How many orders shipped yesterday, and which ones are stuck?" The client calls Kentro's tools and reads the results.
- Delegate to Kentro Assistant. The
askCopilottool hands a question or task to the full assistant, with its skills, memories and learnings, and returns the answer plus a conversation id to continue the thread. - Run the assistant's tools directly. Order and fulfillment summaries, inventory, data queries, reports, the knowledge base, dashboards and more, depending on your permissions. See Tools and permissions.
- Start from built-in prompts. Clients that show MCP prompts list
daily-ops-digestandinvestigate-order.
Who can use it
- Any user of a workspace where Kentro Assistant is on. No admin approval is needed, because a connection carries only the permissions of the user who approved it.
- A user whose permissions limit the assistant to Help Center content gets the knowledge base, tutorial, learning, task and messaging tools only; business data is not reachable through the connection.
- One connection serves one workspace. A user of several workspaces connects once per workspace.
- Connections are listed, and can be revoked, in Kentro IQ under
Assistant>Assistant Settings, in theConnect your AI tools (MCP)panel. Admins see and can revoke every connection in the workspace.
Kentro MCP and the API documentation
Kentro MCP serves your workspace's data through Kentro Assistant, signed in as you. It does not serve the API documentation and it is not a way to build an integration: a coding agent reads the docs as Docs for agents describes, and an integration calls the Channel API or the Store API with an API key.
Let your AI client set it up
Paste this prompt into Claude Code, Codex or another AI client. It connects the client, walks you through the sign-in and checks the connection:
Build it with an AI agent
Have your AI client connect itself to Kentro MCP, sign in through Kentro, and verify the connection. Copy the prompt into Claude Code, Codex, Cursor or another coding agent. The prompt library explains how to run it.
You are helping the user connect this AI client to Kentro MCP, Kentro's remote MCP server. Through it you act as the user in their Kentro workspace, with exactly their permissions, through Kentro Assistant.
Read first:
- https://docs.kentro.io/docs/mcp-overview.md
- https://docs.kentro.io/docs/mcp-connect-claude.md (Claude on the web and Claude desktop)
- https://docs.kentro.io/docs/mcp-connect-coding-agents.md (Claude Code, Codex and other clients)
Facts:
- Production URL: https://apis.kentro.live/kiq/v1/copilot/mcp. Kentro staging URL: https://apis.kentro.dev/kiq/v1/copilot/mcp.
- Remote Streamable HTTP server with OAuth 2.1 sign-in in the browser. There is no package to install, no API key and no token to paste. Never ask the user for their Kentro password.
- The connection belongs to the workspace the user approves it in. A user of several workspaces connects once per workspace.
Ask the user:
1. Which AI client this is, if you cannot tell.
2. Production or Kentro staging.
3. Their workspace key: the first part of their Kentro address (acme in acme.kentro.app). The sign-in page asks for it.
Steps:
- Claude Code: run `claude mcp add --transport http kentro-copilot <URL>`. Then ask the user to run /mcp, select kentro-copilot and complete the browser sign-in.
- Codex: run `codex mcp add kentro-copilot --url <URL>`. Codex discovers the OAuth server and opens the browser sign-in on first use.
- Claude on the web or Claude desktop: you cannot add the connector yourself. Tell the user to open Settings, then Connectors, choose Add custom connector, paste the URL and confirm.
- Any other client: check that it supports remote MCP servers over Streamable HTTP with OAuth 2.1, dynamic client registration and PKCE, and that its redirect URI is https or loopback. If it does not, tell the user it cannot connect; Kentro MCP accepts no API keys or static tokens.
- In the browser, the user enters the workspace key, clicks Continue, signs in, and clicks Approve on the page titled Connect to Kentro Assistant.
Verify, and show the user the results:
- Call getSessionContext and report the workspace name and the user the connection acts as.
- Make one read-only request, for example a summary of today's orders with a direct tool, or ask askCopilot what it can help with in this workspace.
- Tell the user where to see and revoke the connection: Kentro IQ, Assistant, Assistant Settings, panel Connect your AI tools (MCP), Active connections.
If something fails:
- "This connection request has expired": start again; a request lasts 10 minutes.
- "Your workspace's billing needs attention": an admin resolves billing in Kentro first.
- "This workspace is out of Copilot credit": an admin tops up in Billing.
- "Rate limit exceeded. Retry in ...": wait the time shown.
- Only knowledge base and tutorial tools appear: the user's permissions limit the assistant to Help Center content; an admin can change that.
Do not change other MCP servers in the client's configuration, and do not store tokens yourself: the client stores them.
Next steps
Updated about 12 hours ago
Did this page help you?