Can my agent list all detection rules currently active in my SIEM?

Yes. Use the 'list_detection_rules' tool. It returns both custom rules and Elastic prepackaged ML algorithms, which is vital for mapping your MITRE ATT&CK coverage.

How do I whitelist a hostname to resolve a false positive via chat?

Use the 'add_exception' mutation. Provide the Exception List ID and the hostname string. The agent will update the container, implicitly ignoring telemetry matched on this host for any bound rule.

Can I search for security alerts (Signals) using KQL through the agent?

Absolutely. The 'search_signals' tool allows you to retrieve critical alert logs. You can provide an optional KQL query to filter for specific users, hostnames, or process trees within your security telemetry.

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

Name: Elastic 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 Elastic Security through 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 Elastic Security "
            "(10 tools)."
        ),
    )

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

Connect your Elastic Security (SIEM) deployment to any AI agent and take full control of your threat detection and SOC auditing through natural conversation.

Pydantic AI validates every Elastic Security tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through 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

Detection Rule Orchestration — List all configured detection rules and retrieve exact EQL or KQL statements to map MITRE ATT&CK coverage natively
Live Alert Auditing — Search raw generated security signals (alerts) consolidating hostname, user profiles, and IP geolocations into a single view
Rule Lifecycle Management — Create new custom log detection rules or irreversibly purge custom logic from the Kibana SIEM engine to tune your environment
Exception & Whitelisting — List global exception lists and whitelist hostnames inside existing containers to resolve false positives and noise in real-time
Threat Intel Verification — Search for specific rules by name, tag, or MITRE tactic to expedite SOC auditing for newly reported CVEs or ransomware
State Control — Enable or disable existing detection rules to manage noisy triggers across large organizational units seamlessly
System Health Checks — Verify if official Elastic prepackaged rules need updates to ensure lack of latest official threat models is addressed

The Elastic 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 Elastic Security to Pydantic AI via MCP

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

Why Use Pydantic AI with the Elastic Security MCP Server

Pydantic AI provides unique advantages when paired with Elastic 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 Elastic 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 Elastic Security connection logic from agent behavior for testable, maintainable code

Elastic Security + Pydantic AI Use Cases

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

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

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

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

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

Elastic Security MCP Tools for Pydantic AI (10)

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

add_exception

name value to the target exception container, implicitly ignoring telemetry matched on this field for any rule bound to the list. Use explicitly to resolve false positives. Whitelist a hostname inside an existing Exception List

create_rule

Defines immediate risk scores multiplying against asset valuations, generating Elastic Signals tracking MITRE TTPs upon match. Create a new Log Detection Rule tracking malicious Elastic telemetry

delete_rule

Cannot be applied to Elastic Pre-built rules which are managed globally via package updates. Irreversible. Hard-delete a custom Elastic detection rule completely

find_detection_rules

Expedites SOC auditing when evaluating coverage for newly reported CVEs or specific localized threats. Search for specific Elastic rules by name, tag or MITRE tactic

get_prepackaged_rules_status

Identifies if the environment is lacking the latest official threat models targeting Windows, Linux, and Cloud environments. Check if official Elastic prepackaged rules need updates

get_rule

Displays run intervals, severity assignment, index scopes, and explicit reference URLs matching threat intel reports. Get exact details, intervals, and query logic for a distinct Rule

list_detection_rules

g., logs-endpoint*, winlogbeat*). Vital for mapping MITRE ATT&CK coverage against the Elastic schema. List all detection rules configured within the Elastic SIEM

list_exceptions

These lists logically bypass specific rules, preventing SIEM alerts from triggering on known-good administrative behavior like vulnerability scanners. List global exception lists managing detection bypass logic

search_signals

Signals consolidate the triggering payload structure, enriching it with Hostname, User profiles, IP geolocations, and process trees. Search raw generated Elastic Security alerts (Signals)

update_rule

Used explicitly to disable noisy rules triggering false positives across large organizational units, or to re-enable them post-tuning. Enable or Disable an existing Elastic Detection Rule

Example Prompts for Elastic Security in Pydantic AI

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

"Show me all active detection rules tagged with 'Ransomware'"

"Add hostname 'dev-machine-01' to exception list 'global-whitelist'"

"Search for security signals from user 'admin_root' in the last hour"

Troubleshooting Elastic Security MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Elastic Security + Pydantic AI FAQ

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