How to Use the Freshservice MCP in Pydantic AI

Q: How does Pydantic AI connect to the Freshservice MCP Server?

Just install pydantic-ai-slimmcp and then create an MCPToolset instance with your Vinkius server URL. Pass this toolset into your Agent's toolsets list. It's a single line of code to get started.

Q: What happens if the Freshservice API changes and a Pydantic AI tool returns new data?

Pydantic AI will raise a ValidationError. This is its core strength. Your agent won't process incomplete or incorrect data; it will stop and tell you exactly which field from the Freshservice tool didn't match the expected schema.

Q: Is it complicated to define the Pydantic models for all the Freshservice tools?

You don't have to. The MCPToolset handles introspection automatically. It queries the MCP Server to get the schemas for tools like getticketdetails and builds the Pydantic validators for you at runtime.

Add type-safe, validated Freshservice tools to any AI agent with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshservice MCP to Pydantic AI

Create your Vinkius account to connect Freshservice to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Freshservice with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Never Trust, Always Verify

Pydantic AI's main purpose is runtime validation. When your agent calls `get_ticket_details`, the response is checked against a Pydantic model. If the Freshservice API ever returns a malformed or unexpected field, your code will raise a `ValidationError` immediately. This prevents silent data corruption and bugs that are a nightmare to track down. You'll know the instant a `list_it_assets` call returns something weird, instead of finding out after it has polluted your database. It's correctness by default.

Plug Freshservice into Any Model

Pydantic AI is model-agnostic. You can use these Freshservice tools with agents powered by OpenAI, Anthropic, Gemini, or a local model on your machine. The `MCPToolset` works the same way everywhere. This means you aren't locked into a single provider. You can prototype with one LLM and switch to another for production without rewriting your tool logic. Your agent's ability to `create_itsm_ticket` or `get_requester_details` stays consistent.

Build Reliable IT Automation with Pydantic AI

The goal is reliable automation. With Pydantic AI, you can build a script that polls `list_it_problems` and confidently creates tickets, knowing your data structures are sound. The framework forces you to handle the data correctly. This is a huge advantage for background jobs or CI/CD pipelines. An agent that uses `check_itsm_status` before a deployment won't get tripped up by a minor API change. If the response doesn't match the schema, it fails loudly and stops the process.

Setup guide

Set up Freshservice MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "freshservice-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Freshservice tools.",
)

result = await agent.run("List recent Freshservice transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Freshservice. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Freshservice now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Freshservice MCP in Pydantic AI

Just install `pydantic-ai-slim[mcp]` and then create an `MCPToolset` instance with your Vinkius server URL. Pass this toolset into your `Agent`'s `toolsets` list. It's a single line of code to get started.

Pydantic AI will raise a `ValidationError`. This is its core strength. Your agent won't process incomplete or incorrect data; it will stop and tell you exactly which field from the Freshservice tool didn't match the expected schema.

Absolutely. Pydantic AI is designed to be model-agnostic. As long as you have a compatible LLM client, you can use the Freshservice `MCPToolset` with it to perform actions like `create_itsm_ticket`.

You don't have to. The `MCPToolset` handles introspection automatically. It queries the MCP Server to get the schemas for tools like `get_ticket_details` and builds the Pydantic validators for you at runtime.

Your data—tickets, assets, user info—is protected at the transport layer. The connection from Pydantic AI to the Vinkius-hosted server is over HTTPS. Vinkius itself ensures that your specific server instance is isolated and can only be accessed with your unique token.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript