How to Use the Jiminny MCP in Pydantic AI

Q: How do I initialize Jiminny MCP Server in Pydantic AI?

Use the MCPToolset constructor with your server URL to register the Jiminny tools. Pass this toolset into the toolsets argument when initializing your Pydantic AI agent.

Q: What happens if a Jiminny transcript schema changes in Pydantic AI?

If the data returned by gettranscript deviates from the expected schema, Pydantic AI raises a validation error. This prevents your agent from processing malformed conversation data.

Q: How do I list recent sales activities?

Your agent calls listactivities to fetch a list of recent calls. This returns structured metadata that you can parse or filter programmatically.

Build type-safe Pydantic AI agents that validate Jiminny sales transcripts and team metrics at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jiminny MCP to Pydantic AI

Create your Vinkius account to connect Jiminny 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 Jiminny with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe transcript validation in Pydantic AI

Your Pydantic AI agent runs `get_transcript` and validates the returned text structure at runtime. If the Jiminny API returns unexpected formatting, the framework fails loudly instead of letting your agent hallucinate. This strict validation ensures your data pipeline remains clean when extracting conversation data. By integrating this MCP Server, you guarantee that every line of raw Jiminny sales dialogue matches your exact schema before processing.

Validate coaching and call metrics at runtime

When pulling performance metrics using `get_coaching_stats` and `get_call_stats`, your Pydantic AI agent enforces strict type constraints. Numbers stay numbers, and missing fields from Jiminny trigger immediate validation errors. The agent uses `get_action_items` and `get_activity` to build reliable post-call summaries. Because the Jiminny schema is strictly typed, your downstream reporting tools never receive corrupted inputs.

Query organizational schemas with strict types

The agent maps your Jiminny sales hierarchy by running `list_users`, `list_teams`, and `get_user`. Pydantic AI ensures that every user object matches your internal data models precisely. To prevent running queries against an offline API, the agent calls `check_jiminny_status` to verify Jiminny connectivity. This guarantees your type-safe agent only executes when the external service is fully operational.

Setup guide

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

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

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

Use the `MCPToolset` constructor with your server URL to register the Jiminny tools. Pass this toolset into the `toolsets` argument when initializing your Pydantic AI agent.

If the data returned by `get_transcript` deviates from the expected schema, Pydantic AI raises a validation error. This prevents your agent from processing malformed conversation data.

Yes, you can connect to the Jiminny MCP Server using Streamable HTTP or SSE transports. Simply pass the endpoint URL to your Pydantic AI toolset configuration.

Your agent calls `list_activities` to fetch a list of recent calls. This returns structured metadata that you can parse or filter programmatically.

All user profiles and coaching metrics are retrieved through a secure, isolated sandbox. Vinkius handles the API authentication, ensuring your Pydantic AI code never exposes raw credentials during runtime validation.

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