Vanta MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Vanta through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
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 Vanta "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in Vanta?"
)
print(result.data)
asyncio.run(main())
* 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 Vanta MCP Server
Connect your Vanta account to any AI agent and bring continuous security monitoring directly into your conversational workflow.
Pydantic AI validates every Vanta 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
- Personnel Compliance — Rapidly list all active personnel records, fetch specific user security training completion details, or deactivate users directly during employee offboarding.
- Endpoint Fleet — Retrieve data on all computers and physical workstations actively monitored by Vanta, ensuring disk encryption and antivirus SLA compliance.
- Vulnerability Tracking — Monitor unpatched Common Vulnerabilities and Exposures (CVEs) across your cloud infrastructure and verify remediation SLAs in real-time.
- Security Posture — Access public Trust Center configurations, review pending security report requests from customers, and list your internal risk-vetted third-party vendors (subprocessors).
The Vanta 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 Vanta to Pydantic AI via MCP
Follow these steps to integrate the Vanta 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 Vanta with type-safe schemas
Why Use Pydantic AI with the Vanta MCP Server
Pydantic AI provides unique advantages when paired with Vanta 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 Vanta integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Vanta connection logic from agent behavior for testable, maintainable code
Vanta + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Vanta MCP Server delivers measurable value.
Type-safe data pipelines: query Vanta with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Vanta tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Vanta and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Vanta responses and write comprehensive agent tests
Vanta MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect Vanta to Pydantic AI via MCP:
vanta_compliance_status
Shows: overall pass rate percentage, number of passing/failing/warning tests per framework, critical alerts requiring immediate attention, and the audit-readiness score. Use when the user asks "how is our compliance?", "are we ready for the SOC 2 audit?", or needs a quick compliance health check across all frameworks. Get the overall compliance posture dashboard — pass rates per framework, critical alerts, and audit readiness score across SOC 2, ISO 27001, HIPAA, and GDPR
vanta_get_test
Use to drill into a failing test: "why is the MFA test failing?" or "which resources are non-compliant for encryption?" Get detailed information about a specific Vanta compliance test — evidence, linked controls, failing resources, and remediation guidance
vanta_list_computers
Each device shows: device name, OS version, disk encryption status, firewall enabled, antivirus installed, screen lock configured, owner email, and overall compliance status. Use for endpoint compliance audits, device inventory, or identifying non-compliant machines before an audit. List monitored endpoint devices — laptops and desktops with OS version, encryption status, antivirus, and compliance state
vanta_list_evidence_requests
Each request includes: description of the evidence needed, assigned owner, due date, completion status, and linked control. Use during audit preparation: "what evidence is still outstanding?", "who needs to submit screenshots?", or "are we ready for the audit?" List outstanding audit evidence requests in Vanta — documents and screenshots needed from team members with deadlines
vanta_list_integrations
). Each integration shows: service name, connection status (connected/disconnected/error), last sync date, coverage metrics, and any configuration warnings. Use to check integration health, verify coverage, or troubleshoot sync issues. List all connected integrations in Vanta — cloud providers, identity providers, code repos, and their sync status
vanta_list_people
Each person includes: name, email, role, security awareness training status (completed/overdue), device compliance (encrypted/antivirus/updated), access review completion, and employment status. Use for "who has overdue training?", "which employees have non-compliant devices?", or pre-audit personnel reporting. List all personnel in Vanta with security training completion, device compliance, access review status, and onboarding/offboarding state
vanta_list_policies
). Each policy shows: name, approval status (approved/draft/needs review), last review date, next review due, version number, and percentage of employees who have acknowledged. Use for policy management audits or compliance gap analysis. List all security and compliance policies in Vanta — approval status, review dates, version tracking, and employee acknowledgment rates
vanta_list_risks
Each risk includes: title, description, risk category, impact level (1-5), likelihood level (1-5), calculated risk score, linked mitigating controls, treatment plan (accept/mitigate/transfer), owner, and status. Use for risk management reporting, board-level summaries, or identifying high-risk areas that need attention. List the risk register — identified security risks with impact, likelihood, risk score, assigned controls, and mitigation status
vanta_list_tests
Each test maps to a specific control requirement (e.g., "MFA enabled for all users", "Encryption at rest"). Returns test name, associated framework (SOC 2/ISO/HIPAA/GDPR), current status (PASS/FAIL/WARNING), last run date, and any remediation notes. Use when the user asks about compliance posture, failing tests, or audit readiness. List all compliance monitoring tests in Vanta — SOC 2, ISO 27001, HIPAA, and GDPR controls with pass/fail status and last run dates
vanta_list_vulnerabilities
). Each entry includes severity (CRITICAL/HIGH/MEDIUM/LOW), CVE identifier, affected resource/package, discovery date, and SLA deadline for remediation. Use when the user asks about security posture, open vulnerabilities, or needs to prioritize remediation work. List detected security vulnerabilities across your infrastructure — severity, CVE IDs, affected resources, and SLA deadlines
Example Prompts for Vanta in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Vanta immediately.
"List pending Trust Center requests for our security documentation."
"Retrieve the Vanta framework compliance details and mapped status of our organization."
"What subprocessor vendors are we actively syncing in Vanta right now?"
Troubleshooting Vanta MCP Server with Pydantic AI
Common issues when connecting Vanta to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiVanta + Pydantic AI FAQ
Common questions about integrating Vanta MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
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?
Can I switch LLM providers without changing MCP code?
Connect Vanta with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Vanta to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.