How to Use the Uniphore Conversation AI MCP in Pydantic AI

Q: How can I use Uniphore Conversation AI and Pydantic AI together?

You treat the MCP Server as a toolset. Your agent calls getmeeting or gettranscript, and then you pipe that output into a Pydantic validator. This confirms the data is clean before your LLM even sees it.

Q: Which tool should I use for finding meeting context with Uniphore Conversation AI and Pydantic AI?

Start by using listmeetings to get the full list of IDs. If you know what you're looking for, run searchmeetings to narrow it down first. Always establish scope before asking for details.

Guarantee accurate meeting data with Uniphore Conversation AI using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Uniphore Conversation AI MCP to Pydantic AI

Create your Vinkius account to connect Uniphore Conversation AI 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 Uniphore Conversation AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Retrieving Structured Action Items via MCP Server

Use `get_action_items` to get a list of tasks. Since you're using Pydantic AI, the agent doesn't just assume the data is right; it validates that every returned task field (like owner or due date) matches your expected schema. If the API sends back garbage data—unexpected fields or wrong types—the agent fails loudly with a validation error. That means zero silent corruption.

Searching Meetings for Reliable Data

Need to check past conversations? Run `search_meetings` and pass the results into your Pydantic-validated pipeline. This guarantees that even if you find a hundred meetings, when the agent tries to process them, the resulting data structure is correct. It’s about correctness first. If it doesn't fit the model, the agent stops.

Getting Meeting Summaries and Details

The `get_meeting_summary` tool pulls the high-level overview, but because you're using Pydantic AI, that summary text gets validated against a defined output model. You get predictable data structures every single time. This is essential for building mission-critical agents where assumption equals risk.

Setup guide

Set up Uniphore Conversation AI 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": {
        "uniphore-conversation-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You treat the MCP Server as a toolset. Your agent calls `get_meeting` or `get_transcript`, and then you pipe that output into a Pydantic validator. This confirms the data is clean before your LLM even sees it.

The agent fails immediately and loudly with a validation error. It won't process bad fields or hallucinate missing information, which is exactly what you want when building reliable, production-grade systems.

Yes. The MCP Server outputs are inherently compatible because the framework validates them at runtime. You don't have to worry about data format shifts between tools or models.

Start by using `list_meetings` to get the full list of IDs. If you know what you're looking for, run `search_meetings` to narrow it down first. Always establish scope before asking for details.

This MCP Server touches action items and task records. By validating these specific structured outputs, the system helps your agent focus on verifiable commitments rather than general conversation noise.

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