Bring Notification Infrastructure
to CrewAI
Learn how to connect Novu to CrewAI and start using 39 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 Novu MCP Server?
Connect your Novu account to any AI agent and take full control of your notification infrastructure through natural conversation.
What you can do
- Triggering & Events — Trigger single, bulk, or broadcast notifications across Email, SMS, Push, and Chat using workflow identifiers.
- Subscriber Management — Create, retrieve, update, and search for subscribers to maintain an up-to-date communication database.
- Preference Controls — Inspect and update subscriber-specific notification preferences to ensure compliance and user satisfaction.
- Workflow Cancellation — Cancel active or pending workflows, such as digests or delayed notifications, using transaction IDs.
- Tenant Context — Manage notifications within specific tenant contexts for multi-tenant applications.
How it works
- Subscribe to this server
- Enter your Novu Secret Key
- Start triggering and managing notifications from Claude, Cursor, or any MCP-compatible client
No more manual API calls to test your notification flows. Your AI acts as a dedicated communications engineer.
Who is this for?
- Developers — test notification triggers and subscriber updates directly from the code editor without switching to Postman.
- Product Managers — verify workflow payloads and inspect subscriber preferences to troubleshoot delivery issues.
- Growth Teams — automate broadcast notifications for marketing campaigns through simple natural language commands.
Built-in capabilities (39)
Bulk update subscriber preferences
Cancel active or pending workflows (e.g., digests, delays)
Check if a subscriber is subscribed to a topic
Create an environment variable
Create a new integration
Create a new layout
Create a new subscriber
Create a new topic
Create subscriptions for a topic
Create a new workflow
Delete an integration
Delete a message
Delete messages by transaction ID
Delete a subscriber
Delete subscriber credentials
Delete a topic
Delete subscriptions from a topic
Retrieve usage of an environment variable
Retrieve a subscriber by ID
Retrieve subscriber preferences
Retrieve a topic by key
Retrieve a topic subscription
List active integrations
List all environment variables
List all integrations
List messages
List subscriptions for a topic
Search for subscribers
Set an integration as primary
Send a notification to all existing subscribers
Trigger multiple events in a single request
Trigger a notification to one or more subscribers
Update an environment variable
Update an integration
Update an existing subscriber
Update subscriber credentials
Update a subscriber preference
Update a topic
Upsert subscriber credentials
Why CrewAI?
When paired with CrewAI, Novu becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Novu 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
Novu in CrewAI
Novu and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Novu 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 Novu in CrewAI
The Novu 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 39 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
Novu for CrewAI
Every tool call from CrewAI to the Novu MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I send a notification to all my subscribers at once?
Yes! Use the trigger_broadcast tool with your workflow name. This will initiate a notification event for every existing subscriber in your Novu environment.
How do I find a subscriber if I only have their email address?
You can use the search_subscribers tool and provide the email as a parameter. The agent will return the subscriber's full profile, including their unique subscriberId.
Is it possible to stop a notification that is currently in a 'delay' or 'digest' state?
Yes. By using the cancel_trigger tool with the corresponding transactionId, you can halt any active or pending workflow execution before it reaches the final delivery.
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 →
Anyscale
7 toolsOrchestrate your Anyscale infrastructure — manage LLM queries, vectors, services, and cluster batch jobs directly from your AI agent.
Checkout Champ
8 toolsManage CRM and order workflows via Checkout Champ — track leads, monitor orders, and analyze transactions directly from any AI agent.
Markdown Frontmatter Harvester
1 toolsScan local Obsidian or Hugo vaults and extract all YAML frontmatter (tags, dates, status) into a single structured JSON. Let your AI query your scattered notes metadata instantly.
Runlayer
27 toolsAI enterprise control plane: manage MCP servers, skills, agents, and security policies via agents.