mongodb-atlas

mongodb-atlas is a plugin for Claude Code from mongodb/agent-skills. Its manifest loads nothing; the 7 skills it bundles cost 853 tokens per session together, scanned A, original, Apache-2.0.

A connection add-on for MongoDB Atlas, MongoDB's hosted cloud database service, through a managed MCP server. It lets an AI agent work with Atlas data and account resources after you sign in.

In plain words
What is it for?
Use it to inspect Atlas clusters, manage collections and projects, optimize queries, generate MongoDB code, and manage database users or network access.
Why use it?
It provides one route for exploring data, managing database structures, improving queries, and managing Atlas resources. It is intended for Atlas rather than a separate self-managed MongoDB installation.

Plugin for Claude Code ✓ vendor

Written for Claude Code: a Claude Code plugin manifest.

Good fit Use it to inspect Atlas clusters, manage collections and projects, optimize queries, generate MongoDB code, and manage database users or network access.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add mongodb/agent-skills
/plugin install mongodb-atlas
About the project

MongoDB Agent Skills is an official collection of skills and plugins that help AI coding agents work with MongoDB databases, including Atlas and self-managed deployments. Developers use it for query writing, schema design, query optimization, Atlas Search, and vector search. The catalogue entries are MongoDB’s own agent skills, plugins, and setup instructions.

mongodb/agent-skills · 190 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/mongodb/agent-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mongodb-atlas

README.md
[![agentmods](https://agentmods.dev/badge/plugins/mongodb/agent-skills/mongodb-atlas/github.svg)](https://agentmods.dev/plugins/mongodb/agent-skills/mongodb-atlas)
Your own site
<a href="https://agentmods.dev/plugins/mongodb/agent-skills/mongodb-atlas"><img src="https://agentmods.dev/badge/plugins/mongodb/agent-skills/mongodb-atlas/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mongodb-atlas

Your own site · 80×15
<a href="https://agentmods.dev/plugins/mongodb/agent-skills/mongodb-atlas"><img src="https://agentmods.dev/badge/plugins/mongodb/agent-skills/mongodb-atlas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 7 skills cost 853 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

mongodb-atlas scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/mongodb-atlas/.claude-plugin/plugin.json · 33 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "mongodb-atlas",
  "displayName": "MongoDB Atlas (Managed MCP)",
  "version": "1.2.1",
  "description": "Connect to MongoDB Atlas clusters only through the Atlas Managed MCP Server. Sign in with your Atlas account to explore data, manage collections, optimize queries, generate reliable code with MongoDB best practices, and manage Atlas resources such as clusters, projects, database users, and network access.\n\nIf you are running a different MongoDB deployment or want to run a local MongoDB MCP Server, install the MongoDB (Self-Managed MCP) plugin instead.",
  "author": {
    "name": "MongoDB",
    "email": "[email protected]",
    "url": "https://www.mongodb.com"
  },
  "homepage": "https://www.mongodb.com/docs/mcp-server/get-started/",
  "repository": "https://github.com/mongodb/agent-skills",
  "license": "Apache-2.0",
  "keywords": [
    "mongodb",
    "atlas",
    "database",
    "mcp",
    "vector-search"
  ],
  "skills": "./skills/",
  "mcpServers": {
    "mongodb-atlas": {
      "type": "http",
      "url": "https://mcp.mongodb.com/",
      "oauth": {
        "clientId": "https://claude.ai/oauth/claude-code-client-metadata"
      }
    }
  }
}
Contents

What it installs

The manifest is a name and a version. 7 skills travel with it, and installing the plugin installs all of them — 853 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 33 lines scan A 3fbb159c27a3

Subscribe to this mod's changes

mongodb-atlas is a plugin published in the GitHub repository mongodb/agent-skills (190 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.