Kylas MCP Server for Pydantic AIGive Pydantic AI instant access to 7 tools to Create Contact, Create Lead, Get Lead, and more
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Kylas through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
Ask AI about this App Connector for Pydantic AI
The Kylas app connector for Pydantic AI is a standout in the Sales Automation category — giving your AI agent 7 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
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 Kylas "
"(7 tools)."
),
)
result = await agent.run(
"What tools are available in Kylas?"
)
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 Kylas MCP Server
Connect your Kylas account to any AI agent and manage your sales CRM through natural conversation.
Pydantic AI validates every Kylas tool response against typed schemas, catching data inconsistencies at build time. Connect 7 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
- Lead Management — List, create, and inspect leads with status tracking
- Deal Pipeline — Browse deals across pipeline stages with values
- Contact Database — Manage contacts with activity and communication history
- Pipeline Monitoring — Track conversion rates and deal velocity
The Kylas MCP Server exposes 7 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.
All 7 Kylas tools available for Pydantic AI
When Pydantic AI connects to Kylas through Vinkius, your AI agent gets direct access to every tool listed below — spanning pipeline-management, deal-tracking, lead-management, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
Create a new contact
Pass data as a JSON string. Create a new lead
Get specific lead details
List all CRM contacts
List all CRM deals
List all Kylas leads
List CRM tasks
Connect Kylas to Pydantic AI via MCP
Follow these steps to wire Kylas into Pydantic AI. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install Pydantic AI
pip install pydantic-aiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
agent.py and run: python agent.pyExplore tools
Why Use Pydantic AI with the Kylas MCP Server
Pydantic AI provides unique advantages when paired with Kylas 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 Kylas integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Kylas connection logic from agent behavior for testable, maintainable code
Kylas + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Kylas MCP Server delivers measurable value.
Type-safe data pipelines: query Kylas with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Kylas tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Kylas and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Kylas responses and write comprehensive agent tests
Example Prompts for Kylas in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Kylas immediately.
"Show the sales pipeline and deals closing this week."
"Create a new lead and show all contacts at acmecorp.com."
"Show team performance and pipeline conversion metrics."
Troubleshooting Kylas MCP Server with Pydantic AI
Common issues when connecting Kylas to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiKylas + Pydantic AI FAQ
Common questions about integrating Kylas 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.