MC Agent Toolkit plugin

Monte Carlo plugin for Claude Code and Cursor: table checks before queries, data incident triage and monitor creation.

  • 93 ★ on the repository
  • Last commit
  • Apache-2.0
Plugin

Extended access

Why this level

  • Skills read warehouse metadata and can create monitors and change alerts.
  • Hooks fire on dbt and SQL edits and the plugin sends anonymous telemetry.
All reasons and checks

monte-carlo-data/mc-agent-toolkit

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add plugins/mc-agent-toolkit

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Skills read warehouse metadata and can create monitors and change alerts.
  • Hooks fire on dbt and SQL edits and the plugin sends anonymous telemetry.

This is third-party code. Review the repository files before installing.

What it does

Monte Carlo's official toolkit for agents, bringing its data observability platform into the editor. One plugin bundles skills by job: a table health report, alert triage, incident root-cause search, monitor design written as YAML, and analysis of storage cost and slow pipelines. The `prevent` skill fires through hooks when dbt and SQL files are edited. It shows what a change affects and proposes monitors for new logic. The plugin also includes the Monte Carlo MCP server, so no separate connection setup is needed. Skills can also be installed one by one with `npx skills add`.

Who it is for. Analysts and data engineers with a Monte Carlo account who edit dbt models and triage alerts inside Claude Code or Cursor.

Good fit when

  • Before building a report on a table you want to know its freshness and active alerts.
  • An alert fired overnight and the agent has to trace the cause through lineage.
  • A dbt model is changing and its impact on consumers is unknown.
  • The warehouse has few monitors and the team adds them as code.
  • The storage bill is growing and you need tables nobody reads.

Not a fit when

  • You have no Monte Carlo account, so the skills have nothing to read.
  • The task has nothing to do with data quality or observability.
  • Anonymous install telemetry is unacceptable and will not be disabled.

Example request

Check the health of the orders table before I build a report and show active alerts and monitor gaps.

Limitations

A Monte Carlo account with the Editor role or above is required, plus OAuth login to the MCP server. All six editor plugins send an anonymous install event, and the Claude Code and Cortex Code plugins also send skill usage data. Disable it with `MC_AGENT_TOOLKIT_TELEMETRY_DISABLED=1`. The `remediation` skill proposes and runs alert fixes, so confirm steps by hand. The `prevent` skill activates automatically through hooks when dbt and SQL files change.

How to disable. Remove the plugin with the editor's plugin manager. In Claude Code uninstall `mc-agent-toolkit` and disconnect the `monte-carlo-mcp` MCP server through `/mcp`.

FAQ

How do I install the plugin in Claude Code?

Add the marketplace with `/plugin marketplace add monte-carlo-data/mc-agent-toolkit`, then run `/plugin install mc-agent-toolkit@mc-marketplace`. Updates arrive through `claude plugin update`.

Which editors are supported?

Besides Claude Code there are plugins for Cursor, Copilot CLI, OpenCode, Codex and Cortex Code. Guides live in the `plugins/` folder of the repository.

Can I skip the plugin?

Yes. Add the MCP server with `claude mcp add --transport http monte-carlo-mcp https://mcp.getmontecarlo.com/mcp`, sign in through `/mcp` and install a skill such as `npx skills add monte-carlo-data/mc-agent-toolkit --skill prevent`.

What does telemetry send?

An anonymous install identifier, the toolkit version and the editor name. Prompts, skill arguments and code are not sent. Disable with `MC_AGENT_TOOLKIT_TELEMETRY_DISABLED=1`.

Does it work in Claude.ai?

On Claude web and desktop, Monte Carlo is available as a verified connector from the Claude directory. The plugin targets coding agents.

Discussion

No questions or reviews yet.

Plugins

A Claude Code plugin and MCP server: over 1000 scientific tools for biology, chemistry and medicine, data-check commands and routing skills

PluginBroad access1.8KRepository stars
Editors’ pick

The official MathWorks kit that connects an AI agent to MATLAB through an MCP server and curated skills

SkillExtended access1.3KRepository stars
Official

Official Data Commons MCP server: an agent finds statistical indicators and pulls observations for countries, regions and cities.

MCP serverExtended access149Repository stars

A Claude Code agent for protein design: target research, antibody and nanobody generation, screening and candidate ranking.

PluginExtended access119Repository stars
Official

Official Pinecone plugin: an agent creates indexes, searches them, builds a RAG assistant and cites your files.

PluginExtended access68Repository stars
Official

A desktop SQL workspace with a built-in MCP server: the agent reads the schema and runs queries in the same client you already use

MCP serverBroad access5.4KRepository stars

README in short

Skills are grouped by job: trust, incidents, monitoring, prevention, optimization and setup. Workflow skills run the atomic ones in order.

README badge

Report a problem

Foxx AIMC Agent Toolkit
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.