Bring Nosql
to Google ADK
Learn how to connect Azure Cosmos DB Container to Google ADK and start using 4 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Azure Cosmos DB Container MCP Server?
This server strips away dangerous global Azure permissions. It gives your AI agent one surgical superpower: the ability to query, insert, and update documents inside one specific Cosmos DB Container.
By strictly scoping access, your AI can safely manage structured data, store chat histories, and process complex NoSQL queries without ever touching your critical cloud databases.
The Superpowers
- Absolute Containment: The agent is locked to a single container. It cannot list other databases or drop your production data.
- Native Cosmos DB Integration: Direct interactions with Cosmos DB, supporting rich SQL queries and partition management.
- Plug & Play Database: Instantly gives your agent a scalable NoSQL database to store structured memories and application state.
Built-in capabilities (4)
Make sure to provide the ID and Partition Key properties inside the documentJson if required. Create a new document in the Cosmos DB Container
Provide partitionKey if your container requires it. Delete a document from the Cosmos DB Container
Provide partitionKey if your container requires it. Retrieve a specific document by its ID
You can optionally provide parameters in JSON format. Do not include the DB or Container name in the query, Cosmos expects queries like "SELECT * FROM c WHERE c.status = @status". Execute a SQL query against the configured Cosmos DB Container
Why Google ADK?
Google ADK natively supports Azure Cosmos DB Container as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 4 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.
- —
Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution
- —
Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Azure Cosmos DB Container
- —
Production-ready features like session management, evaluation, and deployment come built-in. not bolted on
- —
Seamless integration with Google Cloud services means you can combine Azure Cosmos DB Container tools with BigQuery, Vertex AI, and Cloud Functions
Azure Cosmos DB Container in Google ADK
Azure Cosmos DB Container and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Azure Cosmos DB Container to Google ADK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Azure Cosmos DB Container in Google ADK
The Azure Cosmos DB Container MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 4 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Google ADK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Azure Cosmos DB Container for Google ADK
Every tool call from Google ADK to the Azure Cosmos DB Container MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Why limit the agent to a single Cosmos Container?
To enforce zero-trust security. An autonomous AI agent should not have the ability to read or delete data across your entire Cosmos DB Account (which might include user passwords, financial records, etc.). By scoping it to a single container, you eliminate the risk of catastrophic data loss.
How do I write Cosmos SQL queries here?
You don't need to specify the database or container in the query. Just use the standard alias c. For example: SELECT * FROM c WHERE c.isComplete = false. You can also pass parameters securely.
Do I need to handle Partition Keys?
The query tool automatically enables cross-partition queries to simplify AI workflows. However, for getting, creating, or deleting specific documents, you should provide the partitionKey if your container is configured to require one.
How does Google ADK connect to MCP servers?
Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.
Can ADK agents use multiple MCP servers?
Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.
Which Gemini models work best with MCP tools?
Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.
McpToolset not found
Update: pip install --upgrade google-adk
Explore More MCP Servers
View all →
DataScope
6 toolsCreate mobile forms for field inspections, audits, and data collection that work offline and sync when connectivity returns.
IBGE Full Access — Dados Brasileiros
15 toolsThe ultimate Brazil data Mega-Server: 15 tools spanning census, cities, CNAE economy, name trends, survey indicators, IBGE news, and country comparisons — all of Brazil's official statistics in one zero-auth integration.
ReferralCandy
16 toolsConnect your AI agents to ReferralCandy to manage referral programs, track advocates, register purchases, and analyze campaign performance.
GorillaDesk
12 toolsManage field service operations — schedule jobs, invoice customers, and update notes via AI.