How to Use the Jokes API (API Ninjas) MCP in Pydantic AI

Q: How do I initialize the Jokes API (API Ninjas) in Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset with your HTTP endpoint. Pass the toolset directly to the agent's constructor to expose getrandomjoke.

Get type-safe, runtime-validated humor in your Pydantic AI agents using the Jokes API (API Ninjas) MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jokes API (API Ninjas) MCP to Pydantic AI

Create your Vinkius account to connect Jokes API (API Ninjas) 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 Jokes API (API Ninjas) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict runtime validation for Jokes API (API Ninjas)

The `get_random_joke` tool integrates with your Pydantic AI agent to validate the returned payload against rigid type schemas at runtime. If the API Ninjas response changes format or contains unexpected null fields, the execution fails immediately. This strictness prevents corrupted string payloads from breaking down-stream UI components. By using this MCP Server, you guarantee that only properly formatted joke strings reach your application layer.

Type-safe status checks using Pydantic AI schemas

The `check_api_status` tool returns a boolean indicator which Pydantic AI validates at runtime to ensure your agent receives a clean true/false value. If the status check returns an unexpected format, the framework throws a validation error. This keeps your system predictable and prevents silent failures in production environments.

Model-agnostic MCP Server execution

The `get_random_joke` and `check_api_status` tools work uniformly across any LLM provider supported by Pydantic AI using the `MCPToolset`. This means you can switch your underlying reasoning model without rewriting your joke-fetching logic. The type-safety guarantees remain identical across all model changes.

Setup guide

Set up Jokes API (API Ninjas) 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": {
        "jokes-api-api-ninjas-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Jokes API (API Ninjas) 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 Jokes API (API Ninjas). 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 Jokes API (API Ninjas) 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 Jokes API (API Ninjas) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` with your HTTP endpoint. Pass the toolset directly to the agent's constructor to expose `get_random_joke`.

Pydantic AI will raise a validation error instantly. The framework prevents raw, malformed payloads from `get_random_joke` from corrupting your application state.

No, do not use the deprecated class. You should use the unified `MCPToolset` to connect to your Vinkius server over Streamable HTTP or SSE.

Yes. Pydantic AI is model-agnostic, meaning your local models can call `get_random_joke` just as easily as commercial cloud APIs.

The server runs inside an ephemeral, zero-trust V8 sandbox. Only the raw joke text and API status payloads are transmitted, and Vinkius ensures your Pydantic AI validation schemas are kept private.

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