How to Use the Curator.io MCP in Pydantic AI

Q: How do I configure Curator.io in Pydantic AI?

Install pydantic-ai-slimmcp. Define your server using the unified MCPToolset("http://...") approach, and pass it as toolsets=toolset to your Agent.

Q: Why did Pydantic AI deprecate MCPServerHTTP for Curator.io?

The framework moved to the unified MCPToolset class to handle both SSE and Streamable HTTP transports cleanly. You just pass the Vinkius MCP Server endpoint URL directly.

Build type-safe Curator.io agents with Pydantic AI to validate every social media post and moderation rule 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 Curator.io MCP to Pydantic AI

Create your Vinkius account to connect Curator.io 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 Curator.io with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe social data with Pydantic AI

The `list_feed_posts` tool returns social content that Pydantic AI instantly validates against your exact schema requirements. If an Instagram post arrives missing a timestamp or source origin, the agent fails loudly rather than silently corrupting your database. This strict validation applies across all model choices. Whether you run OpenAI or a local Llama model, the agent receives guaranteed, structured data when it calls `list_social_feeds`.

Audit connections via MCP Server

Calling `list_social_connections` gives your agent structured identifiers and authentication states for every connected account. Because the response is strictly typed, your agent never hallucinates a connection status or misinterprets an OAuth failure. When verifying ingestion gateways, the agent runs `list_feed_sources`. It receives a clean list of Twitter and Instagram parameters, proving your data pipelines pull from the correct origins.

Extract moderation rules accurately

Invoking `list_moderation_rules` pulls your keyword filters and exclusion patterns directly into a validated Pydantic model. You know exactly which rules are active without worrying about unexpected JSON structures breaking your downstream logic. To check the exact configuration of a specific stream, the agent uses `get_feed_details`. It parses the design configurations and metadata, giving you absolute certainty about your current setup.

Setup guide

Set up Curator.io 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": {
        "curatorio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]`. Define your server using the unified `MCPToolset("http://...")` approach, and pass it as `toolsets=[toolset]` to your Agent.

The framework moved to the unified `MCPToolset` class to handle both SSE and Streamable HTTP transports cleanly. You just pass the Vinkius MCP Server endpoint URL directly.

The framework throws a runtime validation error immediately. Your agent will not proceed with hallucinated fields if `get_account_details` returns an unexpected structure.

Yes. Pydantic AI is completely model-agnostic. You can connect local models or commercial APIs to process your social feeds and moderation rules.

Vinkius manages the actual API credentials in an isolated, ephemeral sandbox. Your MCP agent only receives the specific account identifiers and usage limits you request, with zero exposure of underlying OAuth tokens.

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