How to Use the Freshsales (Sales CRM & Lead Scoring API) MCP in Pydantic AI

Q: How do I add the Freshsales MCP Server tools to my Pydantic AI agent?

You simply instantiate the MCPToolset with your Vinkius server URL and pass it into your agent's toolsets list. Pydantic AI handles the discovery and validation, making all 21 Freshsales tools available to your agent.

Build type-safe sales agents for Freshsales with Pydantic AI's runtime data validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsales (Sales CRM & Lead Scoring API) MCP to Pydantic AI

Create your Vinkius account to connect Freshsales (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create records without runtime errors

Stop guessing what the Freshsales API expects. Pydantic AI enforces the rules at runtime. If you try to call `convert_lead` without the required `last_name` and `company_name` fields, your code will raise a validation error immediately. This means you build more reliable agents. Your code won't silently fail or, worse, pollute your CRM with incomplete data. Every call to tools like `create_lead` or `create_contact` is guaranteed to be correctly structured.

Get validated CRM data, every time

When your agent calls `get_lead` or `get_deal`, Pydantic AI automatically parses the JSON response into a Pydantic model. If the API returns an unexpected field or misses a required one, your agent fails loudly instead of continuing with corrupted data. This gives you total confidence in the data you're working with. You're not just getting a dictionary back; you're getting a validated, type-hinted object that your Python code can work with safely. It makes your entire sales automation logic cleaner and easier to debug.

Use any LLM for your Freshsales agent

Pydantic AI is model-agnostic. You can build your sales agent using an OpenAI model, switch to Anthropic's Claude, or even run it on a local model, and your tool-calling code doesn't need to change. Pydantic AI handles the abstraction layer for you. The logic for using `create_appointment`, `update_lead`, and the other 19 tools in this MCP Server remains consistent. You can focus on your agent's strategy, not the specific implementation details of the LLM you're using.

Setup guide

Set up Freshsales (Sales CRM & Lead Scoring API) 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-sales-crm-lead-scoring-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Freshsales (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) MCP in Pydantic AI

It validates every API response against a Pydantic model. If the data structure from a tool like `get_contact` doesn't match the expected schema, it raises a `ValidationError`. This prevents your agent from working with bad or unexpected data.

Your agent will let you know immediately. If a tool starts returning data in a new format, Pydantic AI's validation will fail, protecting your system from processing incorrect information. This makes your automations far more robust.

Yes. Pydantic AI is designed to be model-agnostic. You can connect it to any LLM that supports function calling, whether it's a major cloud provider or a model running on your own machine. Your tool definitions will work the same everywhere.

You simply instantiate the `MCPToolset` with your Vinkius server URL and pass it into your agent's `toolsets` list. Pydantic AI handles the discovery and validation, making all 21 Freshsales tools available to your agent.

Pydantic AI validates data structure, while Vinkius ensures data privacy. All requests from your agent that handle sensitive `lead`, `contact`, or `deal` data are processed in a secure, ephemeral sandbox on Vinkius. The data is never written to disk or logged.

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