# Monte Carlo MCP connector

The Monte Carlo connector brings data alerts, incidents, assets, lineage and monitors into Claude, ChatGPT, Cursor and the Elaichi agent, so your team can investigate data issues from any AI client, inside their own Monte Carlo access.

Source: https://elaichi.ai/connectors/monte-carlo/

## Facts

| | |
| --- | --- |
| Application | Monte Carlo |
| Category | Observability |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Monte Carlo builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | docs.getmontecarlo.com/docs/in-app-support |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Monte Carlo is connected

- Which alerts fired on the orders table overnight?
- Show the upstream lineage for the revenue dashboard table.
- Create a freshness monitor on the customers table.

## Connect Monte Carlo in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Monte Carlo.
2. Optionally set Share with, then press Connect.
3. Approve it in Monte Carlo. Monte Carlo's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Monte Carlo tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Monte Carlo MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Monte Carlo MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Monte Carlo MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Monte Carlo to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Monte Carlo tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Monte Carlo through Elaichi

### Work an alert before the morning standup

Data engineering. Ask what fired overnight in Monte Carlo, pull the details of the alert on the orders table, and get a summary ready before anyone else is awake.

### Trace a broken table back upstream

Data platform. When a table goes stale, follow its lineage in Monte Carlo to find the upstream asset that stopped loading, without clicking through the graph by hand.

### Check a dashboard's source table is healthy

Analytics. Before sending a report, ask whether the assets behind it have open alerts or failed monitors in Monte Carlo, and attach the answer to the email.

### Put a monitor on a key table

Data governance. Describe the table and the check you want, and have a freshness or volume monitor created in Monte Carlo so the next gap is caught early.

### Confirm revenue data is fresh before close

Finance. Ask whether the revenue and billing tables in Monte Carlo loaded on time this month and whether anything is still open before numbers go out.

### Explain why a stakeholder's numbers look wrong

Support. When someone asks why a figure changed, pull the related Monte Carlo incidents and lineage and reply with a plain explanation in minutes.

## Elaichi vs Zapier MCP vs Composio for Monte Carlo

All three can connect Monte Carlo to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Monte Carlo tools | Allow or restrict single Monte Carlo tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Monte Carlo call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Monte Carlo to Claude?

Connect Monte Carlo in Elaichi first: pick it from the catalog, sign in to your Monte Carlo account and approve the connection, with no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the address. Claude asks you to sign in to Elaichi, and Monte Carlo alerts, assets and monitors are available in your chats.

### Does Monte Carlo work with ChatGPT and Cursor as well as Claude?

Yes. Once Monte Carlo is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi agent. You connect Monte Carlo once and each person signs in to Elaichi from whichever client they use.

### What can an AI agent actually do with my Monte Carlo data?

An agent connected through Elaichi can review alerts and incidents in Monte Carlo, look up tables and other assets, follow lineage upstream and downstream, and create or update monitors. In practice that means asking what fired on the orders table overnight, which upstream asset caused it, and setting a freshness check so it is caught next time. Short, concrete asks tend to work better than long paragraphs.

### Does connecting Monte Carlo give the AI everything in my workspace?

No. Every call to Monte Carlo runs as the person who signed in, so the agent sees only the assets, alerts and monitors that person can already see in Monte Carlo. Elaichi can narrow that further with restrictions and toolboxes, and it never widens what Monte Carlo itself allows.

### Can my team share one Monte Carlo connection?

Yes. One person connects Monte Carlo in Elaichi and shares the connection with a team, and nobody else ever handles a key or password. Each teammate still signs in to Elaichi as themselves, so the audit log names the person who looked at an alert or created a monitor, not the account owner.

### Can I stop an agent from deleting or changing things in Monte Carlo?

Yes. Restrictions in Elaichi apply per action, so you can allow reading alerts and lineage in Monte Carlo while blocking the creation or removal of monitors. A restricted action is never advertised to Claude, ChatGPT or Cursor, so no prompt can reach it.

### What happens to a Monte Carlo connection when someone leaves?

Offboarding a person in Elaichi ends their access to Monte Carlo through every client at once. A shared Monte Carlo connection keeps working for everyone else on the team. If you want to remove Monte Carlo entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client.

### Does the Monte Carlo MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Monte Carlo is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Monte Carlo?

Yes. Both let Claude, ChatGPT or Cursor use Monte Carlo. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Monte Carlo call.

### How is Elaichi different from Composio for Monte Carlo?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Monte Carlo: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.