DocumentDB Agent Kit is a collection of agent skills, diagnostic scripts, and an MCP server for Azure DocumentDB, a managed database service that provides MongoDB-compatible access while using the DocumentDB project underneath. Developers use it for vector and full-text search, query and connection tuning, deployment, security, high availability, and troubleshooting. The catalogue add-ons are the kit's skills, plugins, agent, and MCP integration.
Borrowing it
Nothing to install: this file belongs to Azure/documentdb-agent-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Azure/documentdb-agent-kit/main/GEMINI.mdgit clone --depth 1 https://github.com/Azure/documentdb-agent-kitWrote 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/azure/documentdb-agent-kit/gemini-md)<a href="https://agentmods.dev/instructions/azure/documentdb-agent-kit/gemini-md"><img src="https://agentmods.dev/badge/instructions/azure/documentdb-agent-kit/gemini-md/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.
<a href="https://agentmods.dev/instructions/azure/documentdb-agent-kit/gemini-md"><img src="https://agentmods.dev/badge/instructions/azure/documentdb-agent-kit/gemini-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00354 | $0.00354 |
| Opus 5.5 | $0.00142 | $0.00142 |
| Sonnet 5.5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
documentdb-agent-kit 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 2mo 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
Azure DocumentDB Gemini Extension
This extension provides tools for managing and optimizing Azure DocumentDB (MongoDB-compatible) deployments using the official documentdb-mcp-server.
Configuration
The extension requires a connection profile to be configured server-side. Set the DOCUMENTDB_CONNECTION_PROFILES environment variable before launching Gemini CLI.
Recommended: Microsoft Entra / OIDC backend authentication
export DOCUMENTDB_CONNECTION_PROFILES='{"sandbox":{"authMode":"entra","endpoint":"<cluster>.mongocluster.cosmos.azure.com","tokenScope":"https://ossrdbms-aad.database.windows.net/.default","allowedHosts":["*.mongocluster.cosmos.azure.com"]}}'
Sign in with Azure CLI for local development:
az login --tenant <tenant-id>
In Azure hosting, use managed identity or workload identity and grant that identity access to the backend database.
Local / sandbox: SCRAM connection string
export DOCUMENTDB_CONNECTION_PROFILES='{"local":{"uriEnv":"DOCUMENTDB_LOCAL_URI"}}'
export DOCUMENTDB_LOCAL_URI='mongodb://localhost:27017'
Tool capability gates
By default only read tools are enabled. To enable higher-impact tools, override in your shell before launching Gemini:
export ENABLE_WRITE_TOOLS=true # insert / update / delete / find_and_modify
export ENABLE_MANAGEMENT_TOOLS=true # drop_database, drop_collection, create_index, ...
If the user needs help configuring the MCP server, use the mcp-setup skill to guide them through the process. For the full list of options, see the DocumentDB MCP Server documentation.
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.
- 2mo ago First seen · 40 lines · 354 tokens per session scan A 3e50b68c11e3
documentdb-agent-kit GEMINI.md is an instructions file published in the GitHub repository Azure/documentdb-agent-kit (6 stars, last pushed 2d ago), licensed MIT. It adds 354 tokens to every session, about $0.0014 per session on Opus 5.5. 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 2026-08-31.
documentdb-agent-kit GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| documentdb-agent-kit GEMINI.mdAzure/documentdb-agent-kit | Instructions file | 6 | 2d ago | MIT | A | 354 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |