Can I block a malicious IP address directly from my agent?

Yes. Using the `create_ip_acl_rule` tool, you can immediately add an IP or CIDR range to your global denylist (black list) to mitigate threats as soon as they are identified during your security audit.

Is it possible to triage vulnerabilities and change their status via chat?

Absolutely. You can use `update_vulnerability_status` to change a vulnerability's lifecycle status (e.g., to closed or false positive) once you have investigated it or applied remediation steps.

Wallarm MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Wallarm
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Wallarm through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Wallarm "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Wallarm?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Wallarm MCP Server

Connect your Wallarm account to any AI agent and secure your API infrastructure through natural conversation.

Pydantic AI validates every Wallarm tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Security Attacks — Monitor and search for active security attacks detected by Wallarm, grouped by vector (SQLi, XSS, etc.)
Granular Hits — Perform deep forensics by searching for individual malicious HTTP request hits with full payloads
Vulnerability Management — List and triage security vulnerabilities discovered in live API traffic directly from your agent
API Inventory — Retrieve the automatically discovered API inventory to see all exposed endpoints and methods
Filtering Nodes — Verify the health and heartbeat status of your deployed WAF and API gateway filtering nodes
IP Control — Audit and manage IP allowlist/denylist rules to immediately block malicious sources or allow trusted partners
Remediation Guidance — Access comprehensive diagnostic data and CWE mappings for specific vulnerabilities

The Wallarm MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Wallarm to Pydantic AI via MCP

Follow these steps to integrate the Wallarm MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Wallarm with type-safe schemas

Why Use Pydantic AI with the Wallarm MCP Server

Pydantic AI provides unique advantages when paired with Wallarm through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Wallarm integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Wallarm connection logic from agent behavior for testable, maintainable code

Wallarm + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Wallarm MCP Server delivers measurable value.

Type-safe data pipelines: query Wallarm with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Wallarm tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Wallarm and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Wallarm responses and write comprehensive agent tests

Wallarm MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Wallarm to Pydantic AI via MCP:

create_ip_acl_rule

list_type must be "white" or "black". Adds an IP or CIDR range to the global allowlist or denylist

get_client_info

Retrieves details about the Wallarm account, subscription, and feature status

get_discovered_api_inventory

Retrieves the API inventory automatically discovered through passive traffic analysis

get_vulnerability_details

Retrieves comprehensive diagnostic data and exploit evidence for a specific vulnerability ID

list_filtering_nodes

Lists all deployed Wallarm WAF/API gateway filtering nodes

list_ip_acl_rules

Lists configured IP allowlist and denylist rules

search_security_attacks

Searches for security attacks detected by Wallarm, grouped by vector (SQLi, XSS, etc.)

search_security_hits

Shows full request headers and payloads for blocked traffic. Searches for granular individual malicious HTTP request hits intercepted by WAF nodes

search_vulnerabilities

Lists all open security vulnerabilities discovered in live API traffic

update_vulnerability_status

Valid statuses: open, closed, falsepositive. Changes the lifecycle status of a vulnerability (e.g., mark as closed or false positive)

Example Prompts for Wallarm in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Wallarm immediately.

"List all security attacks detected in the last hour."

"Block the malicious IP address 1.2.3.4 immediately."

"What vulnerabilities are currently open in our production API?"

Troubleshooting Wallarm MCP Server with Pydantic AI

Common issues when connecting Wallarm to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Wallarm + Pydantic AI FAQ

Common questions about integrating Wallarm MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Wallarm MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.