How to Use the GatherUp MCP in Pydantic AI

Q: How do I make GatherUp tools available to my Pydantic AI agent?

Install the pydantic-ai-slimmcp package, then create an MCPToolset instance with your Vinkius server URL. Add this toolset to the toolsets list when you initialize your Agent.

Q: Can Pydantic AI validate the output from all GatherUp tools?

Yes. Every tool in this MCP server, from getaccountinfo to listcustomercontacts, has a corresponding Pydantic model for its output. Your agent gets runtime validation on every single tool call.

Q: How does Pydantic AI help me reply to reviews from GatherUp more reliably?

When your agent gets a review from listonlinereviews, Pydantic AI ensures it's a valid object. That means when you pass it to replytoonlinereview, you know for certain that fields like reviewId exist and are the correct type, preventing runtime errors.

Build a reliable GatherUp agent that never fails silently with Pydantic AI's runtime data validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GatherUp MCP to Pydantic AI

Create your Vinkius account to connect GatherUp 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 GatherUp with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Prevent Bad Data, Automatically

This MCP server's tools return data that's already structured for Pydantic models. When your agent calls a tool like `list_online_reviews`, the response is checked against a strict schema before your code even sees it. If the API ever sends back something malformed—a missing field, the wrong data type—your agent will raise a `ValidationError` immediately. No more silent failures or corrupted data making its way through your system.

Use Any LLM, Your Choice

Pydantic AI is model-agnostic, and this toolset works everywhere. You can build your GatherUp agent with an OpenAI model today, switch to a local Llama model tomorrow, and the tools will behave exactly the same. The `MCPToolset` abstracts away the model-specific details. Your code for calling `search_all_reviews` or `add_new_customer` doesn't change. You get type-safety and consistency, regardless of the LLM you're using.

Build Correct-by-Construction Agents

Define agent workflows with confidence. For example, have your agent `search_all_reviews` for negative feedback, then pass the result to `reply_to_online_review`. Pydantic's models guarantee that the `review_id` and other fields are present and correctly typed. This eliminates an entire class of runtime errors. You're not just hoping the data is right; you're verifying it at every step. It's a more robust way to build agents that interact with external APIs.

Setup guide

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

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

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

Install the `pydantic-ai-slim[mcp]` package, then create an `MCPToolset` instance with your Vinkius server URL. Add this toolset to the `toolsets` list when you initialize your `Agent`.

Yes. Every tool in this MCP server, from `get_account_info` to `list_customer_contacts`, has a corresponding Pydantic model for its output. Your agent gets runtime validation on every single tool call.

When your agent gets a review from `list_online_reviews`, Pydantic AI ensures it's a valid object. That means when you pass it to `reply_to_online_review`, you know for certain that fields like `reviewId` exist and are the correct type, preventing runtime errors.

This server handles the entire integration layer for you—authentication, HTTP requests, and keeping the models in sync with the GatherUp API. You just focus on the agent's logic, not the plumbing.

Your data, which includes customer contacts and the text of reviews, is only processed in memory. It is never written to disk by the server. The entire environment is ephemeral and access is gated by your private Vinkius token.

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