Bring Real Time Sync
to CrewAI
Learn how to connect PubNub (Real-time Messaging) to CrewAI and start using 31 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 PubNub (Real-time Messaging) MCP Server?
Connect your PubNub account to any AI agent to orchestrate real-time communication, monitor user presence, and manage data streams through natural language.
What you can do
- Real-time Messaging — Publish JSON payloads to any channel and retrieve historical message logs with precise timetokens.
- Presence Monitoring — Track who is online (
here_now), see which channels a user is in (where_now), and manage custom presence states. - User & Channel Metadata — Manage App Context by creating and retrieving user profiles, channel metadata, and memberships.
- Message Management — Count messages sent after specific timestamps or purge history for compliance and storage management.
- File Sharing — Generate upload URLs and manage files stored within the PubNub network.
- Admin & Push — Monitor keyset metrics, manage applications, and configure mobile push notifications (APNS/FCM).
How it works
- Subscribe to this server
- Enter your PubNub Subscribe Key, Publish Key, and UUID
- Start streaming data and managing real-time interactions from your MCP-compatible client
Who is this for?
- IoT Developers — Monitor device heartbeats and send control commands via real-time channels.
- Support Teams — Inspect chat history and user presence to provide better live assistance.
- System Architects — Audit channel metadata and monitor keyset metrics directly from the AI interface.
Built-in capabilities (31)
Create a new PubNub app (Admin API)
Get usage metrics (Admin API)
List all PubNub apps (Admin API)
List all keysets (Admin API)
Delete a file from a channel
Delete message history for channels
Generate a file upload URL
Get all channels (App Context)
Get all users (App Context)
Get a specific channel (App Context)
Get a file URL
Get memberships for a user (App Context)
Get message count for channels
Get message history for channels
Get a specific user (App Context)
List files in a channel
Grant a PAM v3 token
Revoke a PAM v3 token
Get presence state for a user in a channel
Send presence heartbeat
Get current channel occupancy (Here Now)
Leave a channel (Presence)
Set presence state for a user in a channel
Get channels a user is in (Where Now)
Publish a message to a channel
Manage or list push notification channels for a device (APNS v2)
Remove all push notification channels for a device (APNS v2)
Remove a user (App Context)
Set or update a channel (App Context)
Set or update memberships for a user (App Context)
Set or update a user (App Context)
Why CrewAI?
When paired with CrewAI, PubNub (Real-time Messaging) becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call PubNub (Real-time Messaging) 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
PubNub (Real-time Messaging) in CrewAI
PubNub (Real-time Messaging) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect PubNub (Real-time Messaging) 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 PubNub (Real-time Messaging) in CrewAI
The PubNub (Real-time Messaging) 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 31 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
PubNub (Real-time Messaging) for CrewAI
Every tool call from CrewAI to the PubNub (Real-time Messaging) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I check if a specific user is currently online in a channel?
You can use the presence_here_now tool to see a list of all active UUIDs in a specific channel, or presence_where_now to find all channels a specific UUID is currently subscribed to.
Can the AI retrieve past messages from a channel?
Yes, the get_message_history tool allows the agent to fetch historical messages from one or more channels, including metadata and specific time ranges.
Is it possible to manage user profiles and metadata through this server?
Absolutely. You can use set_user to create or update profiles and get_user to retrieve them. You can also manage channel metadata using set_channel and get_channel.
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 →
Shipday
9 toolsDispatch and track local deliveries with driver management, route optimization, and real-time tracking for last-mile operations.
Lyko
12 toolsAccess European public transit via Lyko — plan intermodal trips, check departures, search stops, and monitor transit operators from any AI agent.
freee
9 toolsManage Japanese accounting and business via freee — track deals and invoices, handle partners and expenses, and audit tax codes directly from any AI agent.
Better Stack
10 toolsAutomate incident management via Better Stack — monitor uptime, manage incidents, and control on-call schedules securely from your AI agent.