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.
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.
npx agentmods add instructions/mongodb/agent-skills/gemini-mdgit clone --depth 1 https://github.com/mongodb/agent-skillsWrote 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.
[](https://agentmods.dev/instructions/mongodb/agent-skills/gemini-md)<a href="https://agentmods.dev/instructions/mongodb/agent-skills/gemini-md"><img src="https://agentmods.dev/badge/instructions/mongodb/agent-skills/gemini-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00229 | $0.00229 |
| Opus 5 | $0.00114 | $0.00114 |
| Sonnet 5 | $0.00046 | $0.00046 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
agent-skills GEMINI.md 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 5d 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.
What it actually says
MongoDB Gemini Extension
This extension provides tools for managing and optimizing MongoDB databases using the official MongoDB MCP server.
Configuration
The extension may require authentication to connect to a MongoDB instance. You can configure this using one of the following methods:
-
Connection String (Direct Connection): Set
MDB_MCP_CONNECTION_STRINGto the MongoDB connection string (e.g.,mongodb+srv://user:[email protected]/). -
Atlas Admin API Credentials: Set
MDB_MCP_API_CLIENT_IDandMDB_MCP_API_CLIENT_SECRETfor MongoDB Atlas Admin API access. -
Atlas Local: If Docker is installed, the Atlas Local tools can be used to create and connect to a local MongoDB instance. In this case, no additional configuration is required.
-
Read-Only Mode: Set
MDB_MCP_READ_ONLY=trueto enable read-only mode for the MCP server.
If the user needs help configuring the MCP server, use the mongodb-mcp-setup skill to guide them through the process.
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.
- 5d ago First seen · 22 lines · 229 tokens per session scan A 79ea092def60
agent-skills GEMINI.md is an instructions file published in the GitHub repository mongodb/agent-skills (181 stars, last pushed 2d ago), licensed Apache-2.0. It adds 229 tokens to every session, about $0.0011 per session on Opus 5. 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.
Other instructions, from other repositories
deployplan CLAUDE.md
Claude Code instructions for jsuncar/deployplan, a project described as: Deploy Next.js without Vercel. Supabase-like Postgres + public URL. Agent MCP: npx -y deployplan init.
skill-buddy AGENTS.md
AGENTS.md instructions for konnga/skill-buddy, a project described as: AI Skills Buddy, A desktop workspace for managing, installing, and synchronizing Skills and MCP Servers across AI agents.
lime AGENTS.md
AGENTS.md instructions for limecloud/lime, covering lime 源码仓库指南, 事实源, 工程约束, 协议与质量 and 执行方式.
agent-skills CLAUDE.md
Claude Code instructions for SigNoz/agent-skills: Follow CONTRIBUTING.md for all contribution conventions.
task-tracker-copilot-md backend.instructions.md
Instructions for blitznihar/task-tracker-copilot-md, covering backend instructions (express + mongodb), route handlers, response format, error handling and mongodb/mongoose.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).