How to Use the Bitly MCP in Pydantic AI

Q: How do I check my Bitly link details in Pydantic AI?

Use the getbitlink tool. It provides the full object, which your Pydantic models then validate for your agent's use.

Use Pydantic AI to manage Bitly links with runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bitly MCP to Pydantic AI

Create your Vinkius account to connect Bitly 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 Bitly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate link creation in Pydantic AI

The `shorten_url` tool returns a structure that Pydantic AI checks against your schema. If the response is malformed, the agent crashes before processing bad data. Generating codes with `create_qr_code` is just as safe. Every field in the response is validated, ensuring your agent never handles corrupted image data.

Analyze link data with Pydantic AI

When you call `get_clicks`, the agent enforces type-safety on the numeric results. You get exact counts without worrying about unexpected string types in your logic. Use `get_referrers` to see where clicks originate. The tool response is strictly typed, so your agent knows exactly what kind of data it's handling.

Manage Bitly assets in Pydantic AI

Invoke `list_bitlinks` to get a list of all your links. Pydantic AI verifies the list structure, preventing errors when you iterate through your assets. If you need to change a link, `update_bitlink` performs the operation. Your agent confirms the update based on the validated return object.

Setup guide

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

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

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

It runs the server output through your Pydantic models. If the Bitly API returns a field that doesn't match your type, the agent raises a validation error immediately.

Yes, you add the Bitly MCP server to your toolset. Pydantic AI then exposes the tools for your agent to invoke during its turn.

It is, provided you use the MCPToolset. It supports the standard transport protocols required for your agent to connect.

Use the `get_bitlink` tool. It provides the full object, which your Pydantic models then validate for your agent's use.

The connection is isolated via an ephemeral sandbox. Your link metrics and account metadata are never stored beyond the duration of your agent's request.

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