Bring Nosql
to CrewAI
Learn how to connect Azure Cosmos DB Container to CrewAI 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 CrewAI?
When paired with CrewAI, Azure Cosmos DB Container becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Azure Cosmos DB Container tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
- —
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the
mcpsparameter and agents auto-discover every available tool at runtime - —
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
- —
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
Azure Cosmos DB Container in CrewAI
Azure Cosmos DB Container and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Azure Cosmos DB Container to CrewAI 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 CrewAI
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 CrewAI 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 CrewAI
Every tool call from CrewAI 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 CrewAI discover and connect to MCP tools?
CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
Can different agents in the same crew use different MCP servers?
Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
What happens when an MCP tool call fails during a crew run?
CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
Can CrewAI agents call multiple MCP tools in parallel?
CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
Can I run CrewAI crews on a schedule (cron)?
Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.
MCP tools not discovered
Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
Agent not using tools
Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
Timeout errors
CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
Rate limiting or 429 errors
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.
Explore More MCP Servers
View all →
Channable
8 toolsManage marketplace orders and stock via Channable — track sales, update shipments, and monitor returns directly from any AI agent.
Lanhu
10 toolsProduct design collaboration platform — manage design files, handoffs, and team feedback via AI.
TeamGantt
12 toolsPlan projects with intuitive Gantt charts that show deadlines, dependencies, and team workloads in one visual timeline.
NCREIF
10 toolsAccess institutional commercial real estate data via NCREIF — track property performance, indices, and fund returns directly from your AI agent.