How to Use the Wallarm MCP in Vercel AI SDK

Q: How do I check for vulnerabilities using Wallarm and Vercel AI SDK?

Your agent calls searchvulnerabilities to get a list of all open security issues. The results stream into your UI, letting the end user see exactly which APIs are vulnerable right away.

Q: Does Wallarm help with API traffic analysis for Vercel AI SDK?

Absolutely. You can use searchsecurityhits to pull granular details—including headers and payloads—from any malicious request intercepted by the WAF nodes. This data streams right into your client.

Q: What is the best way to manage IP rules with Wallarm and Vercel AI SDK?

You can use createipaclrule in conjunction with listipaclrules. This allows your user-facing product to show a simple, real-time interface for managing the allowlist or denylist.

Q: Can I view API inventory using Wallarm and Vercel AI SDK?

Yes. The getdiscoveredapiinventory tool automatically pulls in a list of APIs discovered through passive traffic analysis, so you don't have to manually map every single endpoint.

Stream live API security insights into your user interface with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wallarm MCP to Vercel AI SDK

Create your Vinkius account to connect Wallarm to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Wallarm with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor and Manage Wallarm Vulnerabilities

You can fetch all discovered open vulnerabilities using `search_vulnerabilities`. This lets you display a real-time list of security risks directly in your app. You'll also get detailed diagnostic data for specific weaknesses by calling `get_vulnerability_details`. Need to change the status? The tool `update_vulnerability_status` lets your agent mark findings as 'closed' or 'falsepositive', keeping your application dashboard accurate and current.

Search for Malicious API Traffic Hits

When an attack happens, you don't want a generic message. Use `search_security_hits` to retrieve full request headers and payloads from blocked traffic. This lets your UI show the exact data that triggered the block. For a broader view of threats, `search_security_attacks` groups detected issues by vector (like SQLi or XSS), giving users an immediate understanding of the attack type.

Control API Access Rules

Managing who can talk to your APIs is crucial. The `create_ip_acl_rule` tool lets you add specific IP ranges to either a 'white' or 'black' list globally. Your app’s settings panel can manage this flow. Before making changes, run `list_ip_acl_rules`. This shows exactly which IPs are currently allowed or denied access by Wallarm.

Setup guide

Set up Wallarm MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Wallarm tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Wallarm transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Wallarm. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Wallarm now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Wallarm MCP in Vercel AI SDK

Your agent calls `search_vulnerabilities` to get a list of all open security issues. The results stream into your UI, letting the end user see exactly which APIs are vulnerable right away.

Absolutely. You can use `search_security_hits` to pull granular details—including headers and payloads—from any malicious request intercepted by the WAF nodes. This data streams right into your client.

You can use `create_ip_acl_rule` in conjunction with `list_ip_acl_rules`. This allows your user-facing product to show a simple, real-time interface for managing the allowlist or denylist.

Yes. The `get_discovered_api_inventory` tool automatically pulls in a list of APIs discovered through passive traffic analysis, so you don't have to manually map every single endpoint.

This MCP Server primarily handles API traffic and security metadata. Specifically, it manages IP addresses (CIDR ranges), vulnerability IDs, request headers, and payloads.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript