How to Use the Freshsales MCP in Pydantic AI

Q: How does Pydantic AI ensure my Freshsales data is correct?

When your agent uses a tool like getleaddetails, Pydantic AI validates the JSON response from the MCP Server against a Pydantic model. If there's any mismatch, it throws an error instead of letting your agent use bad data.

Q: What's the setup process for Pydantic AI and Freshsales?

It's minimal. After pip install, you create an MCPToolset instance with the server URL provided by Vinkius. You then pass this toolset to your Pydantic AI Agent and it can start calling tools like listcrmdeals.

Bring type-safe, validated access to your Freshsales CRM. Build reliable sales agents with Pydantic AI and stop worrying about bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsales MCP to Pydantic AI

Create your Vinkius account to connect Freshsales 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 Freshsales with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Eliminate CRM Data Corruption

Here's the deal: when your agent calls a tool like `get_deal_details`, Pydantic AI automatically validates the response against a strict schema. If Freshsales ever returns an unexpected field or a string instead of an integer, your agent will raise a `ValidationError` immediately. This means no more silent data corruption. You can trust that the data your agent is working with is exactly what you expect it to be. It makes debugging predictable and prevents your agent from making decisions based on malformed CRM data.

Model-Agnostic Freshsales Access

Use whatever LLM you want—OpenAI, Anthropic, Gemini, a local model—Pydantic AI doesn't care. This MCP server exposes the Freshsales tools, and Pydantic AI handles the logic of calling them and parsing the results correctly, regardless of the underlying model. This frees you from vendor lock-in. You can swap out your LLM for a better or cheaper one without rewriting all your tool-calling logic for `create_crm_lead` or `list_crm_tasks`. The Pydantic AI framework provides the stable, type-safe layer in between.

A Reliable MCP Server for Pydantic AI

Getting started is just one line. You create an `MCPToolset` pointing to the server URL, and all 12 tools are instantly available to your Pydantic AI agent. It’s the fastest way to give your agent structured access to your sales pipeline. Your agent can now reliably perform operations like pulling contact lists with `list_crm_contacts` or checking user assignments with `list_crm_users`. Because every response is validated, you build your automation on a foundation of correctness, not hope.

Setup guide

Set up Freshsales 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": {
        "freshsales-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Freshsales 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 Freshsales. 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 Freshsales 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 Freshsales MCP in Pydantic AI

When your agent uses a tool like `get_lead_details`, Pydantic AI validates the JSON response from the MCP Server against a Pydantic model. If there's any mismatch, it throws an error instead of letting your agent use bad data.

Yes. Pydantic AI is model-agnostic. As long as your local model supports function calling, you can connect it to this server to interact with your Freshsales account.

It's minimal. After `pip install`, you create an `MCPToolset` instance with the server URL provided by Vinkius. You then pass this toolset to your Pydantic AI `Agent` and it can start calling tools like `list_crm_deals`.

This is built for modern Pydantic AI, which relies on Pydantic v2 for its core validation features. You'll get the full benefit of strict parsing and type safety.

Your data's security is handled at the transport layer. This MCP Server uses a dedicated, token-based endpoint for your agent. All data—like the contents of `get_deal_details`—is passed through a secure, ephemeral sandbox and is never logged or stored by Vinkius.

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