documentdb-mcp-setup

Setup instructions for connecting an agentic coding client to the DocumentDB MCP server, a tool that lets an agent work with Azure DocumentDB or another MongoDB-compatible database. Connections are selected through named profiles in the client configuration.

In plain words
What is it for?
Use it to configure the server in Claude Code, Claude Desktop, Cursor, Copilot CLI, Gemini CLI, or VS Code and define the connection profiles it can use.
Why use it?
It provides a consistent setup path while keeping database connection strings and passwords out of chat and runtime tool arguments.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/azure/documentdb-agent-kit/mcp-setup
Any agent
npx skills add Azure/documentdb-agent-kit --skill mcp-setup
Clone the repo
git clone --depth 1 https://github.com/Azure/documentdb-agent-kit

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00084 $0.02806
Opus 5 $0.00042 $0.01403
Sonnet 5 $0.00017 $0.00561
Haiku 4.5 $0.00008 $0.00281

Measured 2d ago against content hash 03d1c65eff9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

documentdb-mcp-setup scanned grade D with 3 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/Azure/documentdb-agent-kit/main/install.sh | bash

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| **Gemini CLI** | `~/.gemini/settings.json` | `mcpServers` |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/Azure/documentdb-agent-kit/main/install.sh | bash
skills/mcp-setup/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DocumentDB MCP Server Setup

This skill guides users through wiring the microsoft/documentdb-mcp server into an agentic client and pointing it at Azure DocumentDB (or another MongoDB-compatible endpoint).

The DocumentDB MCP server is stateless and administrator-controlled: backend connection details live in a CONNECTION_PROFILES JSON map defined in the MCP client's config. Tools never accept a connection string as a runtime argument — they reference a named profile via connection_profile.

Safety: never receive credentials in chat

The DocumentDB connection string is a secret — it contains a username and password that grant database access. The agent MUST follow these rules:

  1. Never ask the user to paste a connection string, password, or token into the chat. Always instruct the user to add the value directly to their local MCP config file themselves (or run the bundled installer, which prompts via stdin instead of chat).
  2. Never read, echo, log, or repeat back a credential the user pasted by mistake. If the user pastes one anyway, respond with: "I won't process that value — please delete it from the chat history and add it directly to your client's MCP config instead," and continue with placeholders only. The agent itself cannot remove messages it has already received — only the user can delete the message from their chat history.
  3. Never run a shell command that would print a credential to stdout.
  4. Never write the credential to any file the agent itself creates or edits. The agent only writes placeholder [USER]:[PASSWORD]@... (square brackets defeat the mongodb://[^:]+:[^@]+@ secret-scanner regex); the user replaces it locally.
  5. Never include a credential in a generated explanation, summary, commit message, or example. Use <redacted> if you must reference its position.

If any step below appears to require a credential value, treat it as a placeholder for the user to fill in locally.

Read the full file on GitHub · 227 lines

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. 2d ago First seen · 227 lines · 84 tokens per session scan D 03d1c65eff9d

Subscribe to this mod's changes

documentdb-mcp-setup is a skill published in the GitHub repository Azure/documentdb-agent-kit (5 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 2,806 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens