How to Use the MintMCP MCP in Pydantic AI

Q: How do I link MintMCP with Pydantic AI?

You instantiate an MCPToolset with your gateway URL and add it to your agent's toolsets list. This provides the agent with access to all configured tools, ready for validation against your Pydantic models.

Q: How does MintMCP ensure privacy for Pydantic AI data?

All traffic is screened by mintmcpevalguardrail to prevent leaks. By validating structured parameter strings, the gateway ensures that only safe, authorized data enters your Pydantic AI pipeline.

Q: Can I audit agent actions in Pydantic AI using MintMCP?

You can. By calling mintmcpfetchauditlogs, you pull the full history of every action your agent performed. This is perfect for debugging why a specific validation error occurred during a Pydantic AI run.

Validate every agent action with MintMCP and Pydantic AI for type-safe, secure operations that fail fast on bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MintMCP MCP to Pydantic AI

Create your Vinkius account to connect MintMCP 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 MintMCP with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe tool execution

Ensure your agent responses match your expectations perfectly. By piping MintMCP outputs through Pydantic AI models, you catch malformed data before it touches your database. No more silent failures or hallucinated fields. If the data doesn't fit your schema, the agent stops immediately, keeping your state consistent.

Secure session management

Control exactly how long your agents have access to your environment. Use `mintmcp_revoke_access_token` to kill sessions the moment a task finishes or if you suspect a breach. This gives you a manual kill-switch for all agent activity. It’s a necessary layer of control for any production-grade Pydantic AI deployment.

Introspective tool discovery

Map your agent capabilities dynamically using `mintmcp_list_available_tools`. This lets your Pydantic AI agents understand exactly what operations they are allowed to perform at any given time. It keeps your agent code clean and decoupled. You don't need to hardcode tool lists, as the server provides the current registry on startup.

Setup guide

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

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

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

You instantiate an `MCPToolset` with your gateway URL and add it to your agent's `toolsets` list. This provides the agent with access to all configured tools, ready for validation against your Pydantic models.

Absolutely. Because Pydantic AI validates every response, any unexpected data from `mintmcp_run_tool_action` triggers a validation error. This prevents corrupted data from polluting your application state.

Yes. It supports both Streamable HTTP and SSE transports. You just need to point your `MCPToolset` to the correct MintMCP endpoint to start communicating.

All traffic is screened by `mintmcp_eval_guardrail` to prevent leaks. By validating structured parameter strings, the gateway ensures that only safe, authorized data enters your Pydantic AI pipeline.

You can. By calling `mintmcp_fetch_audit_logs`, you pull the full history of every action your agent performed. This is perfect for debugging why a specific validation error occurred during a Pydantic AI run.

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