MCP Server

Overview

The Monte Carlo MCP Server connects your AI agent or assistant directly to Monte Carlo through the Model Context Protocol (MCP). Once connected, your agent can investigate alerts, explore assets and lineage, create and manage monitors, and evaluate AI agent performance — all without leaving the tools you already work in, like Claude, Cursor, or VS Code.

Want to see what's possible? Jump to What you can do for copy-paste prompts that get you to value in seconds. The server also publishes ready-to-run prompts for common workflows — see Guided prompts.

An Editor role or above is required.

Get connected

Pick the path that matches how you work. Most Claude users should start with the Claude connector (option 1) — it's the fastest and requires no setup. For other AI agents, use OAuth (option 2). For automations and service accounts, API keys are supported (option 3).

Option 1: Claude connector (recommended for Claude users)

Monte Carlo is available as an Anthropic-verified connector in the Claude Connectors Directory, so there are no keys to manage and nothing to configure.

1. Open the Monte Carlo connector in the directory, or in Claude go to Settings → Connectors and find Monte Carlo.
2. Click Connect. Your browser opens the Monte Carlo login page.
3. Sign in and click Allow access on the consent screen.

That's it — Claude can now interact with your Monte Carlo account. This works on both Claude (claude.ai) and Claude Desktop.

Option 2: OAuth (recommended for all other agents)

Any MCP client that supports HTTP transport with OAuth 2.1 can connect to Monte Carlo with no API keys. Point your client at the endpoint below using HTTP transport; on first connection it opens your browser to sign in and authorize access.

https://mcp.getmontecarlo.com/mcp

Most clients just need the URL. A few common examples:

Command-line clients (e.g. Claude Code) — add the server in one line:

claude mcp add --transport http monte-carlo-mcp https://mcp.getmontecarlo.com/mcp

Config-file clients (e.g. Cursor, VS Code) — add the URL to your MCP config:

{
  "mcpServers": {
    "monte-carlo": {
      "url": "https://mcp.getmontecarlo.com/mcp"
    }
  }
}

VS Code uses a "servers" key instead of "mcpServers"; otherwise the entry is identical. When the client connects, your browser opens to complete authentication. To confirm it's working, ask your agent: "Test the Monte Carlo MCP connection."

Option 3: API keys (advanced)

Use MCP Server keys when you're running a service account, CI/automation, or a client that doesn't support HTTP transport or OAuth. For individual, interactive use, prefer the connector or OAuth above.

MCP Server keys are scoped credentials that work only with the MCP Server — they are not standard API keys, and standard API keys will not work with the MCP Server. Treat the key secret like any other credential and store it securely; if it's exposed, create a new key and revoke the old one.

Step 1 — Create MCP Server keys. Create keys via the UI, CLI, or GraphQL — flip between the tabs below (the CLI method requires MC CLI v0.141.4+):

Settings → API Keys → Add
Choose "MCP server" as the key type, add a description, then click Add.
Copy the Key id and Key secret.

montecarlo mcp create-key --description "Automation key"

mutation CreateMcpIntegrationKey($description: String) {
  createMcpIntegrationKey(description: $description) {
    key {
      id
      secret
    }
  }
}

Step 2 — Add the server to your client. Key-based clients connect through mcp-remote (requires Node.js LTS + npm/npx — see Reference & operations). Add the entry to your MCP config, replacing <KEY_ID> and <KEY_SECRET>:

{
  "mcpServers": {
    "monte-carlo": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.getmontecarlo.com/mcp",
        "--header",
        "Authorization: Bearer <KEY_ID>:<KEY_SECRET>"
      ]
    }
  }
}

If your client has trouble with the Authorization header, use custom headers instead:

"--header", "x-mcd-id: <KEY_ID>",
"--header", "x-mcd-token: <KEY_SECRET>"

To confirm it's working, ask your agent: "Test the Monte Carlo MCP connection."

What you can do

The MCP Server exposes Monte Carlo as a set of tools your agent can chain together. You don't need to know the tool names — just describe what you want. Here are some of the most popular workflows, each with a prompt you can try and the kinds of tools the agent reaches for.

Example: Triage alerts

Find what needs attention and act on it:

What Monte Carlo alerts do we have in the past 3 days? Triage them and let me know what I need to review first.

Tools the agent may use: get_alerts, alert_assessment, update_alert.

Example: Investigate an asset

Understand a table's health and how data flows into it:

Check the health of table X, including its upstream dependencies." / "What are the lineage dependencies of table X?

Tools the agent may use: search, get_table, get_asset_lineage.

Example: Close coverage gaps

Find unmonitored critical tables and propose monitors:

Which critical tables in <use case> have no monitors? Draft monitors for them.

Tools the agent may use: get_use_case_tables, get_monitors, create_or_update_table_monitor.

Example: Agent observability

Monitor the performance and reliability of your AI agents:

Please propose monitoring for agent X.

Tools the agent may use: get_agent_metadata, get_agent_trace, create_agent_metric_monitor.

Guided prompts

Beyond tools, the MCP Server publishes a set of prompts — curated, ready-to-run workflows for common use cases. You pick a prompt, provide inputs, and the agent runs the recommended sequence of Monte Carlo tools for you. Prompts are provided by the MCP server so you always get the latest version.

Some of the available prompts:

• mc-asset-health — check the current health of a table before querying it.
• mc-triage — triage your Monte Carlo alerts so you know where to focus.
• mc-incident-response — full incident orchestration, from triage through root cause to remediation.
• mc-proactive-monitoring — discover coverage gaps and create monitors to close them.

In clients that surface prompts as slash commands (such as Claude Code and VS Code), they appear under the server's namespace, for example:

/mcp__monte-carlo__mc-asset-health
/mcp__monte-carlo__mc-triage
/mcp__monte-carlo__mc-incident-response
/mcp__monte-carlo__mc-proactive-monitoring

The prefix after /mcp__ is whatever name you gave the server in your MCP config (monte-carlo here). If you named it differently, your slash commands will match that name.

When to add the Agent Toolkit

The MCP Server connects your agent to Monte Carlo. The Agent Toolkit goes a step further and teaches it how to use those tools well — with pre-built skills, workflows, and hooks for monitoring, triage, and code-change validation.

Reach for the toolkit when you are:

• Working in a coding agent like Claude Code or Cursor.
• Looking to get the most out of Monte Carlo, just like a seasoned engineer would.
• Wanting advanced capabilities, such as automatic risk analysis for every code change.

Explore the Agent Toolkit → · View on GitHub →

Reference & operations

Toolsets, network access control, security, troubleshooting, and Node/curl setup are covered on a dedicated page: Reference & operations.