How to Use the TrueFoundry MCP in Pydantic AI

Q: How does TrueFoundry ensure data correctness with Pydantic AI?

The MCP Server's tools, like truefoundrygenerateembeddings, produce data that your agent validates against Pydantic models at runtime. It guarantees the output structure matches what you expect.

Q: Can I inspect available tool schemas with TrueFoundry and Pydantic AI?

Yes, use truefoundrygetmcpserverinfo to extract the exact JSON metadata for any registered tool. This lets your agent confirm what fields it can expect.

Q: What status checks are available with TrueFoundry and Pydantic AI?

You use truefoundrygetdeploymentstatus to get detailed metric states on the orchestration matrix bounds. This confirms a service's operational readiness for your typed code.

Q: Does TrueFoundry support multiple model queries with Pydantic AI?

While truefoundryrungatewaychat handles the chat query, the core value for Pydantic AI is ensuring that whatever data comes back—from any underlying model—is validated and typed.

Build type-safe systems with Pydantic AI. Validate every MCP Server response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TrueFoundry MCP to Pydantic AI

Create your Vinkius account to connect TrueFoundry 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 TrueFoundry with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structured Embedding Generation

To ensure data correctness, you calculate semantic vectors securely using `truefoundry_generate_embeddings`. Since the output is typed, your agent can validate that the resulting embedding array conforms to expected models. This process makes sure that even if an upstream service changes its format, your Pydantic AI system fails loudly with a validation error, not silent corruption.

Validating MCP Server Tools

Before using a tool, you extract the exact JSON metadata of any registered TrueFoundry tool schema via `truefoundry_get_mcp_server_info`. This allows your Pydantic AI framework to pre-validate expected inputs and outputs. Knowing this structure lets you build agents that are correct first, period. You don't care about speed; you care about the data.

Checking Deployment Readiness on MCP Server

You check service health by calling `truefoundry_get_deployment_status`. This emits detailed metric states on the orchestration matrix bounds, letting your agent know if a backend process is stable. Running this status check before execution prevents type-safe agents from failing due to unexpected infrastructure issues.

Setup guide

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

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

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

The MCP Server's tools, like `truefoundry_generate_embeddings`, produce data that your agent validates against Pydantic models at runtime. It guarantees the output structure matches what you expect.

Yes, use `truefoundry_get_mcp_server_info` to extract the exact JSON metadata for any registered tool. This lets your agent confirm what fields it can expect.

You use `truefoundry_get_deployment_status` to get detailed metric states on the orchestration matrix bounds. This confirms a service's operational readiness for your typed code.

While `truefoundry_run_gateway_chat` handles the chat query, the core value for Pydantic AI is ensuring that whatever data comes back—from any underlying model—is validated and typed.

The server touches model schema JSON metadata. This is critical because your framework validates every field, ensuring that no unexpected or un-typed fields accidentally leak into your application logic.

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