Monte Carlo MCP server

What the model can do

Monte Carlo data observability: alerts and incidents on tables (freshness, volume, schema, custom SQL, metric and dbt failures) by status, severity, type, owner and table over a window of up to 65 days, monitors with their status, last and next run and recent incident counts, catalog search for tables and other assets, and connected warehouses; when you ask, can set an alert's status or name, declare or clear an incident severity, assign an owner, comment, pause, resume, snooze, run or delete a monitor.

Reads

• montecarlo_list_alertsMonte Carlo alerts (incidents are alerts with a severity), newest activity in the window: title, type, status, incident severity, priority, owner…
• montecarlo_get_alertOne Monte Carlo alert by its id, with the same fields as montecarlo_list_alerts.
• montecarlo_list_monitorsMonte Carlo monitors: name, type (freshness, volume, metric, custom SQL, validation...), status (enabled, disabled, snoozed, error, training...)…
• montecarlo_search_assetsSearches Monte Carlo's catalog for tables, views, fields, reports and jobs by name: display name, type, MCON (the id other tools take), warehouse…
• montecarlo_list_warehousesWarehouses and other data sources connected to Monte Carlo that this key can see: name, connection type, id, and how many monitors each has.

Acts, when you ask

These change something in Monte Carlo. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• montecarlo_update_alertSets a Monte Carlo alert's status (ACKNOWLEDGED, WORK_IN_PROGRESS, FIXED, EXPECTED, NO_ACTION_NEEDED, FALSE_POSITIVE…
• montecarlo_set_alert_severityDeclares a Monte Carlo alert an incident with a severity (SEV_1 most severe to SEV_4)…
• montecarlo_set_alert_ownerAssigns a Monte Carlo alert to the Monte Carlo user with this email, who is notified and shown as its owner.
• montecarlo_comment_on_alertPosts a comment on a Monte Carlo alert, visible to everyone who can see the alert; with comment_id…
• montecarlo_delete_alert_commentPermanently deletes a comment from a Monte Carlo alert.
• montecarlo_pause_monitorPauses a Monte Carlo monitor so it stops collecting data and raising alerts (pause true), or resumes it (pause false).
• montecarlo_run_monitorRuns a Monte Carlo monitor now, outside its schedule.
• montecarlo_snooze_monitorSnoozes a Monte Carlo monitor for a number of minutes: it keeps collecting data but reports no anomalies until then.
• montecarlo_unsnooze_monitorEnds a Monte Carlo monitor's snooze so it reports anomalies again.
• montecarlo_delete_monitorPermanently deletes a Monte Carlo monitor; its checks stop and its configuration is gone.

Connect it

First connect Monte Carlo on Dashboard → Connections, then add Memtro to your client once. The Monte Carlo tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Monte Carlo connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › Which data incidents opened this week, and who owns them?
• › Which freshness alerts are still unacknowledged?
• › Which monitors are snoozed or in error right now?
• › Is the orders table monitored, and in which warehouse?
• › Mark the alert on the payments table as acknowledged.

Questions

Is this an official Monte Carlo MCP server?

No. It is Memtro's MCP server with Memtro's Monte Carlo connector behind it: the connector reads Monte Carlo through its API with the credentials you connect on Dashboard → Connections, and Monte Carlo publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Monte Carlo?

Only when you ask, and only what it has been granted: set an alert's status (acknowledged, fixed, expected and so on) or rename it; declare an alert an incident with a severity, or clear it; assign an alert to an owner; comment on an alert, or edit a comment; delete an alert comment; pause or resume a monitor; run a monitor now; snooze a monitor for a number of minutes; unsnooze a monitor; delete a monitor. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Databases and warehouses

• Postgres MCP server
• MySQL and MariaDB MCP server
• SQL Server MCP server
• BigQuery MCP server
• Snowflake MCP server
• AWS Athena MCP server