How to Use the Freshsales MCP in Pydantic AI

Q: How do I initialize the Freshsales MCP server in Pydantic AI?

Use the unified MCPToolset class and pass it your Vinkius HTTP URL. Then, include that toolset in the toolsets array when defining your Agent.

Q: How does Vinkius protect the Freshsales data my Pydantic AI agent reads?

Any text pulled via listnotes or getcontact passes through a zero-trust, ephemeral sandbox. Vinkius authenticates the request, executes the tool, and instantly destroys the environment, ensuring your proprietary sales conversations are never stored.

Build type-safe sales agents by connecting Pydantic AI to Freshsales to guarantee strict data structures for every CRM interaction.

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

Pydantic AI MCP Server Validation

The `create_lead` tool requires a last name and accepts an optional email, and Pydantic AI enforces this schema strictly at runtime. If the underlying language model tries to submit a lead without a last name, the framework fails loudly with a validation error. You never have to worry about silent data corruption in your CRM. The agent catches hallucinated fields immediately, forces a retry, or halts the execution before bad data hits your pipeline.

Fetch Contacts and Deals

When your agent calls `get_contact`, `get_lead`, or `list_deals`, Pydantic AI maps the JSON response directly to your defined data models. You get typed Python objects back instead of unpredictable dictionary structures. This model-agnostic approach means you can swap between OpenAI, Anthropic, or local models without rewriting your CRM logic. The parsing rules remain identical regardless of which LLM generated the tool call.

Audit Tasks and Appointments

Expose `list_tasks`, `list_appointments`, and `list_notes` via the unified `MCPToolset` class. Your agent reads the unstructured text from sales calls and categorizes it into strict data models for downstream reporting. Setup requires just a single HTTP endpoint string passed to the toolset constructor. The framework manages the SSE or Streamable HTTP connection natively, dropping the deprecated MCP server classes for a cleaner implementation.

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-alternative-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

Use the unified `MCPToolset` class and pass it your Vinkius HTTP URL. Then, include that toolset in the `toolsets` array when defining your Agent.

The framework catches schema mismatches before the request leaves your machine. If an agent tries to call `create_lead` without the required last name, a runtime validation error triggers immediately.

Yes. The framework is entirely model-agnostic. As long as your local model supports tool calling, it can interact with the CRM endpoints just like a hosted model.

Strict type safety. You get absolute certainty that the data returning from `list_deals` or `list_leads` via the MCP integration matches your exact Python models, eliminating silent application crashes.

Any text pulled via `list_notes` or `get_contact` passes through a zero-trust, ephemeral sandbox. Vinkius authenticates the request, executes the tool, and instantly destroys the environment, ensuring your proprietary sales conversations are never stored.

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