How to Use the LiteLLM (LLM Proxy & Spend Tracking) MCP in Pydantic AI

Connect your MCP Server to Pydantic AI to validate proxy keys and team budgets with strict runtime types.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiteLLM (LLM Proxy & Spend Tracking) MCP to Pydantic AI

Create your Vinkius account to connect LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe MCP Server Management with Pydantic AI

Stop worrying about malformed gateway configurations. This MCP Server ensures that every response from tools like `get_key_info` and `get_team_info` is strictly validated against Pydantic models at runtime. If the gateway returns unexpected metadata, your agent catches the validation error immediately. This prevents corrupted budget states or incorrect key configurations from silent execution.

Strict Model Deployment and Lifecycle Tracking

Manage your routing endpoints without type errors. Your agent can execute `create_model` or `delete_model` with guaranteed schema enforcement, ensuring fallback paths are structured correctly. The agent queries `get_model_info` to verify fallback targets before shifting production traffic. This guarantees that your fallback chains are structurally sound before any model swap occurs.

Validated Key Generation and Spend Auditing

Provision API credentials with zero schema guesswork. When your agent calls `generate_key`, the output is verified against strict types, ensuring your microservices receive valid keys and budgets. You can audit user consumption by calling `get_user_info` and processing the structured USD spend logs. This makes it easy to run automated budget enforcement scripts that never fail due to parsing issues.

Setup guide

Set up LiteLLM (LLM Proxy & Spend Tracking) 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": {
        "litellm-llm-proxy-spend-tracking-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to LiteLLM (LLM Proxy & Spend Tracking) tools.",
)

result = await agent.run("List recent LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM. 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 LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) MCP in Pydantic AI

Use the MCPToolset class pointing to your Vinkius HTTP endpoint. Pass the toolset instance into your Agent constructor to give your model type-safe access to the gateway tools.

The framework wraps the server tools in Pydantic models. When the agent calls `get_key_info`, the JSON response is parsed and validated against these models, failing loudly if any field is missing or typed incorrectly.

Yes, the server manages routing for any model configured in your proxy, including local setups. Your agent can use `create_model` to register local endpoints and query them using `get_model_info`.

No, MCPServerHTTP is deprecated in Pydantic AI. You should use the unified MCPToolset approach with Streamable HTTP or SSE transports to connect to your Vinkius server.

The MCP Server only accesses LiteLLM proxy metadata, such as key bounds, user IDs, and routing configurations. All communications are isolated within the Vinkius V8 sandbox, ensuring your underlying API keys and query payloads remain 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