Skip to main content
Docs navigation

Claude.ai

Connect Claude.ai to emisar over remote MCP. OAuth signs you in, so you do not need to copy an agent key.

Using Claude Code, Cursor, Claude Desktop, or a CLI instead? Those connect through the emisar-mcp stdio bridge (see Connect a CLI agent). For ChatGPT, see ChatGPT.

Before you start, you need:
  • An account with at least one runner online. Otherwise the agent signs in fine and finds an empty catalog with nothing to call. New here? Run the quickstart first, then come back to connect your LLM.
  • A publicly reachable HTTPS server URL. The URL connection in these guides cannot reach localhost or a private network address. If you run emisar privately, use a local AI client that can reach it instead.
  • Runners that do not require signed dispatch. Claude.ai and ChatGPT do not create emisar dispatch signatures, so a runner that requires one needs the local MCP bridge with a signing key and certificate instead.

Add the connector#

On Claude Team or Enterprise, an organization owner must first add emisar under Organization settings → Connectors → Add → Custom → Web using the values below. Members then open Customize → Connectors, select Connect, and sign in to emisar.

  1. Open Connect an agent in emisar and select Claude.ai.
  2. In Claude, open Customize → Connectors and choose Add custom connector.
  3. Fill in the Connector name and the URL field:

    Connector name

    emisar

    Remote MCP server URL

    https://emisar.dev/api/mcp/rpc
  4. Leave Advanced settings (OAuth Client ID / Client Secret) empty. You do not need to create OAuth credentials. Click Add, then Connect.
  5. Claude opens an emisar tab. Sign in, review what the connector is asking for, and click Authorize.
  6. Turn it on for a chat. Open + → Connectors in the composer and enable emisar.

Optional: open Customize → Connectors → emisar. Under Tool permissions, set both Read-only tools and Write/delete tools to Always allow. This removes Claude's per-tool prompts for emisar. Your emisar policies still decide which actions are allowed, require approval, or are blocked.

Verify the connection#

  1. Ask the client to run linux.uptime on any one of the connected runners.
  2. Confirm that the client returns the action output.
  3. Open Audit. Confirm that the event records the client, runner, action, and reason.

What the sign-in grants#

The consent screen mints a key bound to your membership. The connector acts as you. Every call is attributed to you and the agent you are using. It reaches only the runners and actions your own access already allows (how a key inherits its operator's scope). Revoke it any time from AI agents in the console, or from the connector settings in Claude or ChatGPT.

Last reviewed September 6, 2026

Point your agent at real infrastructure — safely.

Set up a runner first, then connect Claude.ai to your account's MCP endpoint and let policy decide what runs.

Three runners. Seven-day audit. No credit card.