Skillget

mcd-agent-toolkit

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This toolkit is the official agent integration from Monte Carlo, designed to bring data observability, monitoring, and incident troubleshooting directly into AI coding environments like Claude Code and Cursor.

Security Assessment
The tool connects to Monte Carlo's platform using a standard OAuth flow, meaning it handles user authentication securely without requiring hardcoded secrets. The automated code scan checked 12 files and found no dangerous patterns, malicious code, or dangerous permission requests. However, because it is an observability tool, it inherently interacts with your data pipeline's metadata, queries, and schema changes. Network requests are strictly limited to communicating with Monte Carlo's servers. Overall risk is rated as Low.

Quality Assessment
As an officially maintained project by the Monte Carlo team, the underlying code is reliable and was updated very recently. It uses the permissive Apache-2.0 license. The primary drawback is its extremely low community visibility, currently sitting at only 5 GitHub stars. Because of this, there is minimal third-party community scrutiny or widespread validation.

Verdict
Safe to use, provided you already trust Monte Carlo with your data observability and are comfortable with their official OAuth integration.
SUMMARY

Official Monte Carlo toolkit for AI coding agents. Skills and plugins that bring data and agent observability — monitoring, triaging, troubleshooting, health checks — into Claude Code, Cursor, and more.

README.md

mcd-agent-toolkit

Monte Carlo's official toolkit for AI coding agents. Contains skills and plugins that integrate Monte Carlo's data observability platform — lineage, monitoring, validation and alerting — into your development workflow.

Prerequisites

  • A Monte Carlo account with Editor role or above

  • Monte Carlo MCP server — configure with:

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

    Then authenticate: run /mcp in Claude Code, select monte-carlo-mcp, and complete the OAuth flow in your browser.

    Note: The mc-prevent plugin bundles its own MCP server, so if you install the plugin you can skip this step.

    See official docs for other MCP clients and advanced options.

    Legacy: header-based auth (for MCP clients without HTTP transport)

    If your MCP client doesn't support HTTP transport, use .mcp.json.example with npx mcp-remote and header-based authentication. See the MCP server docs for details.

Installing plugins (recommended)

Monte Carlo recommends installing skills via their corresponding plugins. Plugins bundle the skill together with hooks, configuration and additional capabilities that provide a richer experience (e.g., automatic context enrichment from MC lineage data, executing validation queries and synthesizing results in your coding sessions).

Claude Code

  1. Add the marketplace:
    /plugin marketplace add monte-carlo-data/mcd-agent-toolkit
  2. Install a plugin:
    /plugin install mc-prevent@mcd-agent-toolkit
/plugin install mc-generate-validation-notebook@mcd-agent-toolkit
/plugin install mc-push-ingestion@mcd-agent-toolkit
  3. Updates — claude plugin update pulls in the latest skill and hook changes.

Cursor

Run the install script (clones the repo and copies the plugin to ~/.cursor/plugins/local/mc-prevent):

bash <(curl -fsSL https://raw.githubusercontent.com/monte-carlo-data/mcd-agent-toolkit/main/plugins/cursor/prevent/scripts/install.sh)

Or install manually:

git clone https://github.com/monte-carlo-data/mcd-agent-toolkit.git
cd mcd-agent-toolkit
bash plugins/cursor/prevent/scripts/install.sh

Then restart Cursor (or run Developer: Reload Window from the Command Palette). The Monte Carlo MCP server will prompt for OAuth authentication on first use.

Available plugins

Plugin Description
mc-prevent Analyzes schema changes using MC lineage, monitoring, alerts, queries, and table metadata. Generates Monte Carlo monitors and validation queries to prevent data incidents.
mc-generate-validation-notebook Generates executable validation queries from a pull request and packages them into Monte Carlo notebooks for direct testing.
mc-push-ingestion Generates warehouse-specific collection scripts and guides customers through pushing metadata, lineage, and query logs to Monte Carlo.

Using skills directly (advanced)

Skills can also be used standalone without the plugin wrapper. This section is for users who want to submit skills to registries or use them with non-Claude-Code agents. Monte Carlo recommends the plugin approach above for the best experience.

skills.sh (Vercel CLI)

npx skills add monte-carlo-data/mcd-agent-toolkit --skill prevent

Manual installation

Copy to ~/.claude/skills/ or .agents/skills/:

cp -r skills/prevent ~/.claude/skills/prevent

Available skills

Skill Description
prevent Analyzes schema changes using MC lineage, monitoring, alerts, queries, and table metadata. Generates monitors and validation queries to prevent data incidents.
generate-validation-notebook Generates executable validation queries from a pull request and packages them into Monte Carlo notebooks for direct testing.
push-ingestion Generates warehouse-specific collection scripts and guides customers through pushing metadata, lineage, and query logs to Monte Carlo.

Contributing

See CONTRIBUTING.md for guidelines on adding skills, creating plugins, and submitting pull requests.

License

This project is licensed under the Apache-2.0 license — see LICENSE for details.

Security

See SECURITY.md for reporting vulnerabilities.

Yorumlar (0)

Sonuc bulunamadi