Compatible with every major AI agent and IDE
What is the Tailscale MCP Server?
Connect your Tailscale network (tailnet) to any AI agent and take full control of your zero-trust infrastructure through natural conversation.
What you can do
- Device Management — List all nodes in your tailnet, fetch specific device details, authorize new machines, or update device tags to organize your fleet.
- Network Security (ACLs) — Retrieve and update your HuJSON policy files (ACLs) to manage access control without leaving your chat interface.
- Authentication Keys — List, create, and delete auth keys to automate node joining or manage ephemeral server access.
- User Auditing — List all users within your tailnet and fetch detailed profile information for specific members.
- Node Cleanup — Securely delete decommissioned devices from your tailnet using their unique IDs.
How it works
- Subscribe to this server
- Enter your Tailscale API Key
- Start managing your private network from Claude, Cursor, or any MCP-compatible client
No more jumping between the Tailscale admin console and your terminal. Your AI acts as a network administrator that understands your infrastructure context.
Who is this for?
- DevOps Engineers — quickly check node statuses, manage tags, and generate auth keys for CI/CD pipelines.
- Security Teams — audit tailnet users and inspect or update ACL policies to ensure zero-trust compliance.
- IT Administrators — authorize new devices and clean up old nodes from the network via simple commands.
Built-in capabilities (13)
Authorize Device
Create Auth Key
Delete Auth Key
Delete Device
Get Auth Key
Get Device Details
Get Tailnet Policy (ACL)
Get User
List Auth Keys
List Tailnet Devices
List Users
Update Device Tags
Update Tailnet Policy (ACL)
Why CrewAI?
When paired with CrewAI, Tailscale becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Tailscale 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
Tailscale in CrewAI
Tailscale and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Tailscale 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 Tailscale in CrewAI
The Tailscale 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 13 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
Tailscale for CrewAI
Every tool call from CrewAI to the Tailscale MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I update my network's security policy (ACL) using this server?
Yes! You can use get_tailnet_acl to view the current HuJSON policy and update_tailnet_acl to apply changes directly to your tailnet configuration.
How do I authorize a new device that is pending approval?
Use the authorize_device tool with the specific device_id and set the authorized parameter to true. This allows you to manage node entry without the admin console.
Is it possible to generate temporary authentication keys for my servers?
Absolutely. Use the create_auth_key tool. You can optionally provide capabilities like 'ephemeral' or 'reusable' in the JSON payload to define how the key should behave.
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 →
Eventmix
12 toolsOrganize events with integrated registration, payment processing, and attendee communication for conferences and meetups.

Cyberimpact
10 toolsEquip your AI agent to manage email subscribers, monitor campaigns, and track marketing metrics via the Cyberimpact API.

Rocket.Chat
10 toolsConnect your AI assistant to Rocket.Chat to seamlessly send messages, explore channels, manage directories, and orchestrate chat operations directly.

Cognito Forms
12 toolsBuild smart online forms with conditional logic, calculations, and payment collection that adapt to every response.
