MCP for AI agents

Point your MCP host at Kabu and operate the platform from Claude Desktop, Cursor, Grok Build, and other MCP-compatible tools—without pasting broker secrets into the model.

What MCP is for Kabu

The Model Context Protocol (MCP) lets AI hosts call tools on a remote server. Kabu’s MCP product is a standalone HTTPS service—not a local monorepo process and not mounted on the dashboard.

Connect once to https://mcp.usekabu.app. Your host talks Streamable HTTP MCP; Kabu resolves identity server-side and runs the same operator tools available to the dashboard and CLI (experiments, runs, models, deployments, and existing broker accounts).

Remote product host: URL only for OAuth, or URL + Bearer for automation
Same tool registry as the rest of Kabu—no separate agent API to learn
Broker credentials stay with you; agents only reference existing account IDs

Connect in minutes

Preferred path is OAuth Connect: add the URL, sign in in the browser, and the host stores a short-lived token. No API key in host config.

OAuth Connect (recommended)

{
  "mcpServers": {
    "kabu": {
      "url": "https://mcp.usekabu.app"
    }
  }
}

The host discovers authorization metadata from the MCP origin, opens a browser login on Kabu, and then calls tools with the issued Bearer token. Stay logged into Kabu in the browser for the Connect flow. Do not set an Authorization header when you want OAuth—some hosts treat a pre-set Bearer as non-OAuth.

Org API key (automation / hosts without OAuth)

{
  "mcpServers": {
    "kabu": {
      "url": "https://mcp.usekabu.app",
      "headers": {
        "Authorization": "Bearer kabu_live_…"
      }
    }
  }
}

Create keys in the dashboard under Organization → Automation keys (kabu_live_… or kabu_test_…). Use this path for CI or hosts that cannot complete browser OAuth. Revoke MCP OAuth connections under Account → Sessions & connections.

What agents can do

MCP tools are operational: discover context, manage experiments and runs, inspect models and metrics, and work with deployments. They are not a path to paste or store broker secrets.

Experiments — list, get, create, and validate configuration
Training runs — start, resume, cancel; list runs and metrics
Models — list and get artifacts from training
Deployments — list and inspect live deployments; start/stop when enabled for your environment
Brokers (read-only for secrets) — list accounts you already connected and resolve symbols by UUID—not create broker credentials in the model

Connect broker accounts yourself in the dashboard or CLI first. Agents then select an existing account ID for experiments and deployments.

Training · Live trading · Broker accounts

Safety and boundaries

MCP is an operator surface for agents—not a vault and not a place for monorepo install instructions.

Config is only the MCP URL and, for automation, an Authorization Bearer token
No database URLs, org IDs, or vault keys on the AI host
Broker secrets are never accepted as tool arguments
Product endpoint is https://mcp.usekabu.app—a separate service from the dashboard