How to Use the LeadSquared MCP in Pydantic AI

Q: How do I configure the LeadSquared MCP Server within Pydantic AI?

Install the pydantic-ai-slimmcp package and initialize MCPToolset with your Vinkius HTTP URL. Pass this toolset into the Agent constructor to expose all ten tools. Do not use the deprecated MCPServerHTTP class.

Q: Does Pydantic AI validate the output of LeadSquared search queries?

Yes, every response from tools like searchleads or getleaddetails is validated against strict Pydantic schemas. If LeadSquared returns unexpected null values, the framework raises an explicit ValidationError.

Run type-safe LeadSquared CRM operations using Pydantic AI to guarantee zero silent failures in your sales pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LeadSquared MCP to Pydantic AI

Create your Vinkius account to connect LeadSquared 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 LeadSquared with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Lead Ingestion with Pydantic AI

This MCP Server integrates with Pydantic AI to validate every payload before executing `capture_lead` or `create_or_update_lead`. It stops malformed lead data from breaking your CRM integration. If an incoming lead email is invalid or a phone number is missing, the framework raises a validation error immediately. This keeps dirty data out of LeadSquared before it can pollute your database.

Validated Activity Logging

Ensure every logged interaction matches your CRM rules perfectly by letting your agent run `create_prospect_activity` with runtime type-checking. It prevents runtime failures when updating lead timelines. Before writing, the agent queries `list_activity_types` to verify the event schema. It then calls `list_lead_activities` to confirm the write succeeded.

Strict Opportunity Pipelines

Manage your sales pipeline with complete mathematical certainty by letting your agent call `create_opportunity` over the MCP connection. The input parameters are validated against your Pydantic models before hitting the API. Monitor deal status by calling `list_opportunities` and `list_opportunity_activities`. If the API returns unexpected fields, your agent catches the issue instantly instead of processing corrupted data.

Setup guide

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

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

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

Install the `pydantic-ai-slim[mcp]` package and initialize `MCPToolset` with your Vinkius HTTP URL. Pass this toolset into the `Agent` constructor to expose all ten tools. Do not use the deprecated MCPServerHTTP class.

Yes, every response from tools like `search_leads` or `get_lead_details` is validated against strict Pydantic schemas. If LeadSquared returns unexpected null values, the framework raises an explicit ValidationError.

Yes, the framework supports asynchronous tool execution natively. Your agent calls `create_prospect_activity` across multiple leads concurrently without blocking your main event loop.

The framework catches API errors and raises them as standard Python exceptions. Your agent catches these during `create_opportunity` calls and retries or logs the failure gracefully.

All data passing through the MCP Server is processed in memory inside our secure V8 sandbox. Vinkius does not store your LeadSquared API credentials, lead emails, or customer phone numbers. Everything is encrypted and deleted immediately after the tool execution completes.

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