How to Use the Delighted MCP in Pydantic AI

Q: How do I configure Delighted with Pydantic AI?

Install pydantic-ai-slimmcp from pip. Initialize an MCPToolset with your Vinkius Streamable HTTP URL and pass it to your Agent via the toolsets parameter.

Q: Can I search Delighted responses using Pydantic AI?

Calling searchresponsesbycomment allows your agent to find specific text matches. The results map directly to your predefined schema for safe downstream processing.

Bring strict type safety to Delighted using Pydantic AI. Catch API schema mismatches instantly when retrieving NPS scores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Delighted MCP to Pydantic AI

Create your Vinkius account to connect Delighted 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 Delighted with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe NPS with Pydantic AI

Retrieving exact metrics requires the `get_nps_metrics_summary` tool. The agent fetches the real-time breakdown of promoters, passives, and detractors, mapping the JSON directly into your validated Pydantic models. Silent data corruption stops here. If the MCP Server returns a string instead of an integer for the detractor count, the framework fails loudly with a validation error before your agent makes a bad decision.

Validate Customer Histories

Looking up a specific user's past surveys is handled by the `get_person_feedback_history` tool. Your agent pulls all cumulative NPS contributions and associated person attributes in one strict payload. Model-agnostic execution means you swap between Anthropic and local models without changing the tool logic. The agent parses the output from `get_recent_customer_comments` exactly the same way regardless of the underlying LLM.

Strict Survey Triggers

Scheduling a new invitation relies on the `add_person_to_survey` tool. The agent constructs the required payload with exact parameters, ensuring no malformed requests hit the external API. Finding specific user segments works through `list_feedback_contacts`. The agent receives an array of email addresses and survey metadata, validating every single record against your schema before passing the list to your marketing automation system.

Setup guide

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

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

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

Install pydantic-ai-slim[mcp] from pip. Initialize an MCPToolset with your Vinkius Streamable HTTP URL and pass it to your Agent via the toolsets parameter.

Pydantic AI throws a strict validation error immediately. Your agent halts execution rather than hallucinating fields or processing corrupted NPS data.

Calling search_responses_by_comment allows your agent to find specific text matches. The results map directly to your predefined schema for safe downstream processing.

The framework fully supports Streamable HTTP and SSE transports. You configure the unified MCPToolset pointing to your external Vinkius endpoint.

Processing survey responses involves handling raw customer text and contact information. Vinkius operates a stateless proxy, ensuring that PII flows securely into your local runtime without being cached or logged externally by the MCP Server.

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