How to Use the Capsulink MCP in Pydantic AI

Bring strict type safety to your Capsulink operations using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capsulink MCP to Pydantic AI

Create your Vinkius account to connect Capsulink 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 Capsulink with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe link creation for Pydantic AI

Use `shorten_url` to generate links with guaranteed schema validation. If the returned data doesn't match your Pydantic model, the agent fails immediately. This prevents malformed data from poisoning your downstream processes. You always know the structure of the link response.

Validate analytics with Pydantic AI

Run `get_link_daily_stats` and map the output to your typed models. Your agent rejects any response that doesn't fit the expected stats format. It keeps your data logs clean and predictable. You avoid the guesswork usually associated with parsing external API responses.

Manage your account inventory

Call `list_links` to retrieve your current URL set, validated against your custom types at runtime. Your agent can then perform bulk actions with high confidence. Use `edit_link_destination` or `delete_link` to modify your account. Every operation is checked against the server's expected return types.

Setup guide

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

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

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

Initialize the MCPToolset with your server URL and add it to your agent’s tool list. The framework handles the validation of every tool response.

The server provides the schema. Pydantic AI automatically validates the output from any tool like `get_account_info` against those definitions.

Yes. Every request is handled over a secure transport layer. Your sensitive link data never leaves the encrypted channel during the validation process.

The agent will throw a validation error rather than proceeding with bad data. This stops potential issues before they cause downstream silent corruption.

You can, provided the server runs externally. The agent connects to the endpoint and performs all validation logic on the incoming stream.

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