Can the AI forcefully block attackers or does it just view them?

You can explicitly instruct the AI to use the `block_attacker` tool, which triggers a remediation event across your security infrastructure (e.g., WAF integrations). It provides both visibility and direct active response.

Does Salt Security allow me to upload spec definitions (OAS) directly from my files via chat?

Yes, you can upload raw specification content using the `upload_oas_spec` tool for vulnerability testing and validation. Provide the exact OpenAPI content, and Salt will interpret it securely naturally properly successfully cleanly nicely properly natively completely optimally brightly cleanly beautifully actively quickly seamlessly efficiently correctly elegantly faithfully efficiently natively perfectly.

How frequently is the API inventory auto-discovered?

Salt maintains a continuous discovery architecture via passive traffic monitoring. This prevents any drift and immediately identifies 'Ghost APIs' when queried using the `get_inventory` capability.

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

Name: Salt Security
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 Salt Security 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 Salt Security "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Salt Security?"
    )
    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 Salt Security MCP Server

Connect your AI directly with Salt Security to proactively defend your Application Programming Interface (API) environment. Improve API discovery, manage security posture, and remediate threats in real-time through simple conversational prompts.

Pydantic AI validates every Salt Security 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

API Inventory & Discovery — View all auto-discovered APIs in your environment, including unknown or shadow APIs (get_inventory). Retrieve schema details, identify exposed sensitive data (PII), and analyze structural drifts (get_endpoint).
Threat Intelligence & Monitoring — Monitor active API attacks and business logic abuses as they happen (get_attacks). Profile known threat actors to uncover behavioral patterns (get_attackers).
Active Remediation — Respond to incidents immediately by triggering blockade commands against attackers, seamlessly passing instructions to your integrated WAFs (block_attacker).
Posture & Governance Assessment — Identify design flaws and vulnerabilities before they reach production (get_posture_vulnerabilities). Manage OpenAPI (OAS) specifications (list_oas_specs, upload_oas_spec) and verify active governance rules (get_governance_policies).

The Salt Security 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 Salt Security to Pydantic AI via MCP

Follow these steps to integrate the Salt Security 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 Salt Security with type-safe schemas

Why Use Pydantic AI with the Salt Security MCP Server

Pydantic AI provides unique advantages when paired with Salt Security 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 Salt Security integration code

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

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

Salt Security + Pydantic AI Use Cases

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

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

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

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

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

Salt Security MCP Tools for Pydantic AI (10)

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

block_attacker

Issues a command to block a specific attacker

get_attackers

Lists known threat actors profiled by Salt

get_attacks

Lists detected malicious API attacks

get_endpoint

Retrieves details for a specific API endpoint

get_governance_policies

Lists active API governance rules

get_inventory

Retrieves the auto-discovered API inventory

get_posture_vulnerabilities

Retrieves identified pre-production design flaws

get_system_health

Checks the health of traffic mirror ingestion

list_oas_specs

Lists all uploaded OpenAPI specifications

upload_oas_spec

Uploads a new OAS/Swagger specification

Example Prompts for Salt Security in Pydantic AI

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

"List all auto-discovered APIs including shadow and zombie APIs in our infrastructure."

"Are we facing any recent attacks aimed at business logic?"

"Block attacker 'ATT-992' immediately."

Troubleshooting Salt Security MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Salt Security + Pydantic AI FAQ

Common questions about integrating Salt Security 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 Salt Security MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.