How to Use the Tactiq MCP in Pydantic AI

Q: How do I search for specific topics using Tactiq with Pydantic AI?

You use searchtranscripts. The resulting data is validated, meaning your agent gets a clean, predictable list of relevant snippets. It drastically reduces the chance of dealing with unexpected JSON fields.

Q: Can I check the status of Tactiq with Pydantic AI?

Yes, run checktactiqstatus. This tool lets your agent confirm connectivity before attempting any complex data retrieval. It's a simple but critical validation step.

Q: Do I need to know all available recordings when using Tactiq with Pydantic AI?

No, but you can list them using listtranscripts. This gives your agent a reliable index of every recording. It's better than guesswork for planning out complex data flows.

Guaranteed meeting intelligence data using your Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Tactiq MCP to Pydantic AI

Create your Vinkius account to connect Tactiq to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Tactiq with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate and retrieve action items

The `get_action_items` tool pulls out structured tasks, ensuring they fit a predictable schema. This means the output is reliable for your agent to ingest. Since correctness matters most here, Pydantic validation catches any unexpected fields or types in the API response—you won't get corrupted data.

Get detailed transcript content

The `get_transcript` tool pulls the raw text. Because it’s validated against a schema, your agent knows exactly what fields to expect (e.g., timestamp, speaker name, text block). This structured approach means you can build highly reliable components into your overall production system.

List and categorize meeting records

Use `list_meetings` or `list_transcripts` to get metadata for all sessions. These tools provide the necessary index data that guides subsequent, more granular calls. This simple cataloging mechanism is vital; it ensures your agent always knows what data exists before trying to process it.

Setup guide

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

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

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

You use `search_transcripts`. The resulting data is validated, meaning your agent gets a clean, predictable list of relevant snippets. It drastically reduces the chance of dealing with unexpected JSON fields.

This server handles transcripts, summaries, action items, and speaker lists. Every piece of data returned is validated against a specific model, guaranteeing type safety for your agent.

Yes, run `check_tactiq_status`. This tool lets your agent confirm connectivity before attempting any complex data retrieval. It's a simple but critical validation step.

The system fails loudly. Because of Pydantic's built-in guardrails, any data that deviates from the expected schema triggers a validation error. You get an explicit failure instead of silent corruption.

No, but you can list them using `list_transcripts`. This gives your agent a reliable index of every recording. It's better than guesswork for planning out complex data flows.

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