Bring Webhooks
to CrewAI
Learn how to connect Hookdeck (Webhook Gateway) to CrewAI and start using 75 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 Hookdeck (Webhook Gateway) MCP Server?
Connect your Hookdeck account to any AI agent and take full control of your webhook gateway and event-driven architecture through natural conversation.
What you can do
- Connection Management — List, create, and update connections that route events from sources to destinations with specific rules.
- Operational Control — Instantly pause, unpause, enable, or disable connections to handle maintenance or traffic spikes without touching code.
- Source Monitoring — Manage your webhook sources, retrieve their configurations, and monitor the flow of incoming events.
- Infrastructure Auditing — Count active connections and sources to get a high-level overview of your integration health.
- Lifecycle Actions — Delete or update existing infrastructure components as your project requirements evolve.
How it works
- Subscribe to this server
- Enter your Hookdeck API Key
- Start managing your webhook reliability from Claude, Cursor, or any MCP-compatible client
No more jumping between dashboards to pause a failing webhook or check a source configuration. Your AI acts as a dedicated DevOps engineer for your event pipeline.
Who is this for?
- Backend Engineers — quickly debug and manage webhook routes without leaving the terminal or IDE.
- DevOps & SREs — automate the enabling/disabling of connections during deployment windows or incidents.
- Support Engineers — check source configurations and connection statuses to troubleshoot client integration issues.
Built-in capabilities (75)
Bulk cancel events
Bulk retry events based on a query
Bulk retry rejected requests
Cancel an ongoing bulk retry
Cancel a scheduled retry for an event
Count connections
Count destinations
Get issue count
Count sources
Count transformations
Create a bookmark
Can include inline source/destination. Create a connection
Create a destination
Create an issue trigger
Create a source
Create a transformation
Delete a bookmark
Delete a connection
Delete a destination
Dismiss an issue
Delete an issue trigger
Delete a source
Delete a transformation
Disable a connection
Disable a destination
Disable a source
Enable a connection
Enable a destination
Enable a source
Retrieve a specific attempt
Retrieve a bookmark
Get status of a bulk retry
Retrieve a specific connection
Retrieve a destination
Retrieve a specific event
Get event raw body data
Retrieve an issue
Retrieve an issue trigger
Delivery attempt pattern metrics
Event processing and success rate metrics
Failures grouped by issue metrics
Monitor processing backlogs
Request volume and status metrics
Transformation performance metrics
Retrieve a specific request
Retrieve events generated by a request
Retrieve ignored events for a request
Get request raw body data
Retrieve a source
Get a specific transformation execution
Retrieve delivery attempts
Retrieve bookmarks
Retrieve connections
Retrieve destinations
Retrieve events
Retrieve issue triggers
Retrieve issues
Retrieve requests
Retrieve sources
Get transformation executions
Retrieve transformations
Events will be marked as HOLD. Pause a connection
Send events directly to Hookdeck
Retry a specific event
Retry a rejected request
Test a transformation
Replay the bookmarked request
Unpause a connection
Update a bookmark
Update a connection
Update a destination
Update issue status
Update an issue trigger
Update a source
Update a transformation
Why CrewAI?
When paired with CrewAI, Hookdeck (Webhook Gateway) becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Hookdeck (Webhook Gateway) 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
Hookdeck (Webhook Gateway) in CrewAI
Hookdeck (Webhook Gateway) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Hookdeck (Webhook Gateway) 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 Hookdeck (Webhook Gateway) in CrewAI
The Hookdeck (Webhook Gateway) 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 75 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
Hookdeck (Webhook Gateway) for CrewAI
Every tool call from CrewAI to the Hookdeck (Webhook Gateway) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I pause a specific webhook connection if my destination server is undergoing maintenance?
Yes. Use the pause_connection tool with the Connection ID. This will hold incoming events until you use unpause_connection to resume delivery.
How do I see all the active sources currently receiving webhooks?
Simply ask the agent to run list_sources. It will return a list of all configured sources, including their IDs and current status.
Is it possible to get a quick count of how many connections I have configured?
Yes, the count_connections tool provides the total number of connections in your Hookdeck project instantly.
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 →
Wati
13 toolsSend WhatsApp messages at scale with official API access, chatbot automation, and shared team inbox for business conversations.
Toast
10 toolsManage restaurant orders, menus, employees, labor, tables, and payments for your Toast POS through natural conversation.
FastSpring
10 toolsManage digital commerce via FastSpring — track orders and subscriptions, handle accounts, and manage product catalogs directly from any AI agent.
Legal Deadline Calculator Engine
1 toolsCompute rigorous procedural deadlines in business days without risking LLM mathematical hallucination.