Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the MongoDB in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Query a MongoDB database directly: introspect collections and their field shapes, and run read-only find queries with filter, projection, sort and limit. Installs read-only; credentials are held encrypted rather than in the connection string.
Try asking
Example prompts for MongoDB
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → MongoDB, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
MongoDB + Gemini
Query a MongoDB database directly: introspect collections and their field shapes, and run read-only find queries with filter, projection, sort and limit. Installs read-only; credentials are held encrypted rather than in the connection string.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
MONGODB_HOST, MONGODB_PORT, MONGODB_DATABASE, MONGODB_USER, MONGODB_PASSWORD, MONGODB_AUTH_SOURCE
Step 1 — Get credentials
Setup
- Create a user with only
readon the database the agent should see:use admin db.createUser({ user: "amcp_reader", pwd: "change-me", roles: [{ role: "read", db: "shop" }] }) - Set
MONGODB_HOST,MONGODB_PORT(27017),MONGODB_DATABASE,MONGODB_USERandMONGODB_PASSWORD.
MONGODB_AUTH_SOURCE is the field that decides whether this works at all. MongoDB authenticates a user against the database the user was created in, not the one you want to read. A root or admin account created the usual way lives in admin, so MONGODB_AUTH_SOURCE must be admin even though MONGODB_DATABASE is shop. …
Step 2 — Install the adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Step 3 — Add the connector in Gemini
Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (
https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide showsYOUR_SERVER_ID.
Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
"headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
}
}
}
- Get your MCP API key from AnythingMCP → MCP Servers → your server → API keys.
- Save the file and restart
gemini. - Run
/mcpinside the Gemini CLI —MongoDBshould be listed as available. - Vertex AI Studio: pass
https://cloud.anythingmcp.com/mcp/YOUR_SERVER_IDto thetoolsarray of your request with the sameX-API-Keyheader.
Available tools
| Tool | What it does |
|---|---|
mongodb_schema | Introspect the database: every collection, its estimated document count and the field names and types inferred from a sampled document |
mongodb_find | Run a read-only find |
mongodb_find_recent | Read the most recent documents of one collection, newest first by a timestamp field |
mongodb_matching | Return the documents of one collection matching a filter, projecting only their ids, so a population can be sized without transferring it |
mongodb_query_examples | Show worked MongoDB query specs for this connector: filters, operators, projection, sort and the limits that apply |
FAQ
Does Gemini 1.5 Pro or 2.x support MCP? Yes — Gemini CLI ≥ 0.4 and Vertex AI tools API both accept MCP httpUrl connectors with custom headers.
Next steps
- Connector landing page
- Connect to Claude
- Connect to ChatGPT
- Connect to Cursor
- Connect to Meta Muse
- Connect to Microsoft Copilot
Was this guide helpful?