How to Use the Agency Elephant MCP in Pydantic AI

Q: How do I connect Agency Elephant to Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset class with your Vinkius HTTP endpoint. Pass that toolset directly into your Agent constructor.

Q: What happens if Agency Elephant returns unexpected data to Pydantic AI?

The framework fails loudly. If an endpoint like listcampaigns returns a schema that does not match your Pydantic model, the execution stops immediately to prevent silent corruption.

Build type-safe insurance agents by connecting Agency Elephant to Pydantic AI via this MCP Server. Catch bad data before it hits your CRM.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agency Elephant MCP to Pydantic AI

Create your Vinkius account to connect Agency Elephant 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 Agency Elephant with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Agency Elephant MCP Server

Agency Elephant prevents bad data from ruining your marketing automation and commission tracking. When your agent calls `create_lead`, Pydantic AI validates the payload against your exact schema before the request ever leaves your server. If the phone number format is wrong, the framework throws a loud validation error. This strictness applies to reading data as well. Executing `get_lead_details` returns a structured payload that your agent parses into a guaranteed model. You never have to worry about hallucinated fields breaking your downstream insurance reporting.

Reliable drip campaign execution

Agency Elephant ensures you never fire off the wrong email sequence to a client. Your agent queries the system using `list_campaigns` and `list_lead_groups` to build a valid map of available marketing assets. Once it knows the exact IDs, it safely executes `trigger_drip_campaign`. Because you run this on Pydantic AI, you can swap between OpenAI, Anthropic, or local models without rewriting how the agent interacts with these endpoints.

Organize agency workspaces

Agency Elephant requires precision when managing your team roster and lead distribution. The agent calls `list_workspace_users` to pull the active directory, then runs `list_leads` to see how prospects are currently distributed across your staff. If a user needs to be reassigned, the agent handles it by executing `add_lead_to_group`. Every step of this process is strictly typed, meaning your agent cannot accidentally pass a string into an integer ID field.

Setup guide

Set up Agency Elephant 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": {
        "agency-elephant-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` class with your Vinkius HTTP endpoint. Pass that toolset directly into your Agent constructor.

Yes. The framework natively supports both Streamable HTTP and SSE transports. Just provide the correct URL scheme from your Vinkius dashboard when initializing the toolset.

The framework fails loudly. If an endpoint like `list_campaigns` returns a schema that does not match your Pydantic model, the execution stops immediately to prevent silent corruption.

You can. The framework is completely model-agnostic. As long as the model supports tool calling, it can interact with your insurance CRM regardless of who hosts the weights.

Every request routes through an auth-handled Vinkius endpoint. Your prospect lists, agent commission structures, and drip campaign content are processed in a zero-trust environment that leaves no persistent footprint.

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