Prisma Access MCP for AI. Audit your network policies and threat logs in a single query.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Prisma Access connects network security audits to any AI agent via MCP. It lets you run complex checks on your entire SASE environment, from auditing security policies (`get_policies`) to checking global PoP connectivity (`get_service_endpoints`).
Use it to review threat logs, analyze traffic patterns, and verify which remote users are connected right now.
What your AI can do
Get locations
Lists mobile user locations and remote networks for topology review or routing troubleshooting.
Get policies
Retrieves a list of all security policies enforced in Prisma Access, useful for auditing SASE compliance.
Get service endpoints
Lists the global service endpoints (PoPs) available through Prisma Access to check regional connectivity.
Lists all security policies currently enforced by Prisma Access, letting you check for compliance gaps.
Pulls recent threat detection data. You get the severity, details of the attack, and what action was taken against it.
Gets network traffic logs to analyze usage patterns or debug why certain users can't access resources.
Lists Prisma Access service endpoints (PoPs), confirming regional reach and connectivity options.
Lists mobile user locations and remote networks, giving you a map of your current network footprint.
Retrieves a list of all remote users currently connected to the Prisma Access system.
Ask an AI about this
Prisma Access: 7 Tools for Network & Security Audits
These seven tools let you audit every layer of the network stack—from user identity to global service endpoint status—without leaving your AI chat.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Prisma Access on VinkiusGet Locations
Lists mobile user locations and remote networks for topology review or routing troubleshooting.
Get Policies
Retrieves a list of all security policies enforced in Prisma Access, useful for...
Get Service Endpoints
Lists the global service endpoints (PoPs) available through Prisma Access to check...
Get Threat Logs
Pulls recent threat detection logs, including severity and action taken, for...
Get Traffic Logs
Retrieves network traffic logs to help analyze usage patterns or debug access issues...
Get Tunnels
Lists active SD-WAN and network tunnels, helping monitor connectivity status or diagnose tunnel drops.
Get Users
Lists all remote users connected to Prisma Access for auditing access or identifying inactive accounts.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Prisma Access integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Prisma Access, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Prisma Access. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 7 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Checking network status used to mean jumping through five different web dashboards.
You know the drill. A user reports a connection error, so you check the VPN dashboard for active users. Then you open the policy console to verify the rules. After that, you have to jump to the global PoP map to see if the region is even supported. You spend twenty minutes copy-pasting IDs and checking timestamps across three different screens.
With Prisma Access MCP Server, your agent handles this whole sequence in one shot. Need to know who’s connected AND what rules apply? Just ask. The agent executes `get_users` and `get_policies`, giving you the correlated data set without leaving the chat.
Prisma Access MCP Server: Get a full audit of policies, threats, and endpoints.
Before this server, checking threat logs meant manually correlating timestamps between `get_threat_logs` and the actual user identity list. It was slow, error-prone work that required deep knowledge of the system's internal IDs.
Now, you just ask for 'all security violations involving remote users.' The agent handles the joins, running the relevant tools to deliver a single, clean report. It’s instant network visibility—no more dashboard clicking.
What your AI can actually do with this
Prisma Access lets your AI agent punch through your network security data. Forget logging into a dozen different dashboards just to check if everything's running right. This server gives your agent direct access to run complex checks across your entire SASE environment, letting you audit policies, track threats, and verify who’s connected—all from one place.
Auditing Network Policies: You can use get_policies to pull a full list of every security rule Prisma Access enforces. This is critical for compliance audits; it lets you check for any gaps or rules that might be too permissive across your setup.
Tracking User Status and Connectivity: Your agent uses get_users to pull a current list of all remote users connected to the system, helping you audit access immediately or spot accounts sitting there doing nothing. To monitor how those connections are actually running, it calls get_tunnels, which lists all active SD-WAN and network tunnels, letting you check connectivity status or diagnose if a tunnel just dropped.
Mapping Network Topology: If you need to know where your users are operating from, the agent runs get_locations. This tool lists mobile user locations and remote networks, giving you an instant map of your current network footprint for routing troubleshooting or general topology review.
Monitoring Traffic Flow: To figure out why someone can't access a resource or just analyze how much bandwidth people are using, the agent runs get_traffic_logs. This retrieves detailed network traffic logs so you can analyze usage patterns or debug specific access issues quickly.
Investigating Threats and Service Health: When something goes wrong, your agent hits the data hard. It calls get_threat_logs to pull recent threat detection records. These logs give you the severity level of an attack, the details of what was compromised, and what action Prisma Access actually took against it. For regional reach checks, the agent uses get_service_endpoints, which lists all global service endpoints (PoPs) available through Prisma Access; this confirms your regional connectivity options across the board.
Comprehensive Data Retrieval: You can also check the overall health of the system using get_policies for a comprehensive view of enforcement rules, and you can run get_service_endpoints to verify that all global points of presence are active. It’s designed so your agent doesn't have to jump between tools; it pulls everything together.
This setup gives your AI client the raw data—the policies, the logs, the connections—so you don't gotta waste time clicking around in a dozen different web consoles. You just tell it what you need, and it gets the facts.
019d75f9-97de-71a1-ae4b-928eeaec57d1 
Here's how it actually works
The bottom line is: instead of running three different scripts or checking three separate dashboards, your agent runs all necessary network and security checks using one prompt.
Tell your AI client what you need: 'Check for suspicious activity on user accounts.'
The agent recognizes this is a networking task and invokes get_threat_logs and get_users in sequence.
Your client receives structured data containing the list of active users alongside recent threat detections, allowing you to review anomalies immediately.
Who is this actually for?
Security Engineers who spend too much time clicking through multiple vendor dashboards. Network Architects needing to verify global PoP status against compliance rules. Compliance Officers who have to prove that every remote connection is logged and policy-checked.
Uses get_threat_logs and get_policies together to investigate an incident, quickly verifying if the attack falls outside established security rules.
Runs get_locations and get_service_endpoints to map out network gaps or validate connectivity plans for new office deployments.
Uses get_users and get_policies to generate an audit report, confirming that all remote accounts adhere to current company security standards.
What Changes When You Connect
See who’s connected right now: Use get_users to instantly list all remote clients. This is faster than checking the VPN console, especially during an incident.
Verify global coverage: Run get_service_endpoints to confirm if a new region has available PoPs before deployment. You can't plan without knowing your physical reach.
Deep dive into attacks: Combine get_threat_logs with get_policies. The agent shows you not just what happened, but whether the action violated an existing rule.
Debug connectivity quickly: If users complain about slowness, run get_traffic_logs and then check get_tunnels to see if the flow is blocked or failing at the tunnel level. It saves hours of manual troubleshooting.
Audit network shape: Use get_locations to map out your entire remote footprint in minutes. This helps you identify any unexpected, unauthorized endpoints accessing your resources.
See it in action
Investigating a suspected data breach
A security engineer gets an alert about unusual activity. They ask their agent to run get_threat_logs and then cross-reference the timestamps with get_traffic_logs. The agent finds suspicious outbound traffic patterns linked to specific user IDs, narrowing down the scope of the breach instantly.
Verifying compliance for a new region
A network architect needs to connect an office in a new country. They run get_service_endpoints first to confirm local PoP availability, then use get_policies to ensure the existing corporate security rules will apply correctly to that endpoint.
Debugging intermittent VPN drops
A field team reports constant tunnel disconnects. The agent runs get_tunnels and sees multiple flapping links. They then check get_users to see if a sudden spike in connected users correlates with the tunnel instability, pointing to potential capacity issues.
Onboarding an executive account
A compliance officer needs to confirm the new exec's access is minimal. They run get_policies to review all rules and then use get_users to ensure only their specific credentials are logged as active, preventing over-privileging.
The honest tradeoffs
Looking at logs without context
Running only get_traffic_logs and seeing a high volume of data. The user assumes it's malicious but doesn't know if the traffic is authorized or expected.
First, run get_policies. Check if the observed traffic type (e.g., SSH) is allowed by policy. Then, verify who generated that traffic using get_users to assign accountability.
Assuming all endpoints are covered
A developer assumes their branch office uses a primary PoP simply because the main HQ does. They miss regional connectivity gaps.
Always run get_service_endpoints to get a comprehensive list of global Points of Presence (PoPs). This verifies your actual network coverage, not just what you expect.
Ignoring account status
Finding an anomaly in get_threat_logs and immediately assuming it’s a breach. The threat could be from an authorized, but currently inactive, user.
Always cross-reference the suspicious activity against get_users. This confirms if the account was active within the expected window before the incident occurred.
When It Fits, When It Doesn't
Use this server if your job requires continuous monitoring of network state: who's connected, what policies are active, and where the traffic is flowing. It’s perfect for security audits or diagnosing connectivity issues in a complex SASE environment.
Don't use it if you only need to know about one thing—like just user emails or general corporate directory data. For those simple lookups, a standard identity management tool works better. This server is overkill if you just need a single list of names; it’s built for analyzing the relationships between users, policies, and actual network packets.
Questions you might have
How do I check if an old user account is still active using get_users? +
Run get_users and filter the results by last login date. This tool lists all connected remote users, so you can quickly identify accounts that haven't logged in recently or are flagged as inactive.
Can I check if my security policies are blocking a specific type of traffic? +
Yes. First, use get_policies to list the rules. Then, you can compare those policies against what is being captured in your network flow data via get_traffic_logs to find potential gaps.
What should I check if users complain about slow connections? +
Check connectivity in steps: 1) Run get_tunnels for tunnel status. 2) Check get_service_endpoints to validate local PoP health. 3) Review get_traffic_logs to see if bandwidth is maxed out.
How do I check for a recent breach event? +
The quickest way is running get_threat_logs. This tool pulls the most critical data, including severity and attack details. If you spot an ID, run get_users to see which user owned that connection.
How can I use get_locations to map out our remote network topology? +
This tool lists mobile user locations and remote networks. You get a clear view of every connected endpoint, letting you audit your overall coverage area and understand where users are physically connecting from.
What should I check with the get_tunnels tool if we suspect intermittent network drops? +
It lists all active SD-WAN and network tunnels. You can monitor connectivity status here, verifying tunnel links and identifying exactly which connections are dropping or showing instability.
How do I use get_service_endpoints to verify our PoP list for DNS routing? +
This tool lists all Prisma Access service endpoints (PoPs). You confirm the physical locations and services available, which is necessary for setting up optimal regional connectivity and verifying DNS records.
If a user reports an access issue, how does running get_traffic_logs help me debug the connection? +
It retrieves recent network traffic logs. You analyze this data to pinpoint specific usage patterns or determine exactly at which point the connection is failing.
We've already built the connector for Prisma Access. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 7 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.