How to Use the Cloutly MCP in Pydantic AI

Q: How do I set up Cloutly with Pydantic AI?

Run pip install "pydantic-ai-slimmcp" and initialize MCPToolset pointing to your Vinkius HTTP URL. Pass this toolset directly to your Agent definition.

Q: Does Cloutly support type-safe validation in Pydantic AI?

Yes, every tool response like listpendingreviews is validated against Pydantic models at runtime. The agent will reject any payload that does not match the strict schema.

Q: Can I search reviews by author?

Yes, use the searchreviewsbyauthor tool to find specific customer records. The response is parsed and validated into a type-safe Python object instantly.

Q: How does Cloutly protect customer emails?

Customer contact details processed by sendreviewinvite are strictly validated in-memory and routed through encrypted SSE transports. This ensures zero data persistence on intermediate nodes.

Run type-safe review operations in Pydantic AI using validated Cloutly tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloutly MCP to Pydantic AI

Create your Vinkius account to connect Cloutly 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 Cloutly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate review data with Pydantic AI

The `list_reviews` tool retrieves a list of reviews across connected sources, filtering by business and pagination. Your Pydantic AI agent validates every incoming review against strict schema models before processing. If the API returns an unexpected data format, your agent fails loudly with a validation error. This prevents corrupt text or broken metadata from polluting your downstream customer support databases.

Post verified replies via this MCP Server

The `reply_to_review` tool posts a reply to a review on its original platform. Your agent uses this tool to publish responses, verifying that the payload matches your strict internal formatting rules before sending. You configure this by importing the MCP configuration from the unified `pydantic-ai-slim[mcp]` package. Because the old HTTP class is deprecated, this unified toolset handles the SSE transport safely.

Search customer reviews securely in Pydantic AI

The `search_reviews_by_author` tool searches for reviews from a specific customer by name. Your agent uses this tool to look up customer history before triggering any follow-up campaigns. This search ensures you never send a generic `send_review_invite` message to a customer who has already left a detailed five-star review.

Setup guide

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

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

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

Run `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` pointing to your Vinkius HTTP URL. Pass this toolset directly to your `Agent` definition.

Yes, every tool response like `list_pending_reviews` is validated against Pydantic models at runtime. The agent will reject any payload that does not match the strict schema.

If the review data doesn't match the schema, the framework raises a validation error. This keeps your agent from acting on malformed or corrupted API responses.

Yes, use the `search_reviews_by_author` tool to find specific customer records. The response is parsed and validated into a type-safe Python object instantly.

Customer contact details processed by `send_review_invite` are strictly validated in-memory and routed through encrypted SSE transports. This ensures zero data persistence on intermediate nodes.

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