How to Use the EPA Computational Toxicology MCP in Pydantic AI

Q: How do I use EPA Computational Toxicology with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your Vinkius URL. Pass it into your Agent under the toolsets parameter.

Q: Should I use MCPServerHTTP or MCPToolset?

Use MCPToolset. The older MCPServerHTTP method is deprecated in Pydantic AI. The new toolset approach handles the unified Streamable HTTP connection.

Enforce strict type safety on EPA chemical queries with Pydantic AI and MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EPA Computational Toxicology MCP to Pydantic AI

Create your Vinkius account to connect EPA Computational Toxicology 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 EPA Computational Toxicology with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Physical Properties

`get_physicochemical_properties` and `get_fate_and_transport` return predicted melting points, logP values, and bioconcentration metrics. Pydantic AI validates every single float and string returned by the EPA database at runtime. If the upstream API changes a field from an integer to a string, your agent fails loudly. You catch the validation error immediately instead of silently writing corrupted data to your database. You connect the MCP server using `MCPToolset` over a Streamable HTTP transport and let Pydantic handle the strict type checking.

Type-Safe Hazard Queries via MCP Server

`get_hazard_summary` and `get_bioactivity_summary` pull ToxValDB and ToxCast high-throughput screening data. Your AI client retrieves acute systemic toxicity markers and endocrine disruption metrics based on specific DTXSIDs. You don't want an LLM hallucinating a safe bioactivity threshold. Because Pydantic AI binds the MCP tool outputs to strict models, the agent only processes the exact numerical values returned by the EPA endpoints. It strips out the uncertainty.

Resolve Regulatory Lists

`get_chemical_lists` and `get_chemical_synonyms` resolve complex regulatory mappings. The agent takes an obscure trade name, runs a search, and returns the exact regulatory, research, and commercial lists the compound appears on. You build this workflow using the `pydantic-ai-slim[mcp]` package. The framework is model-agnostic. You can run these chemical registry checks using Anthropic, Gemini, or a local model, and the validation guarantees remain identical across the board.

Setup guide

Set up EPA Computational Toxicology 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": {
        "epa-computational-toxicology-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent EPA Computational Toxicology 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 US EPA CompTox. 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 EPA Computational Toxicology 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 EPA Computational Toxicology MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your Vinkius URL. Pass it into your Agent under the `toolsets` parameter.

Yes. Every response from the EPA database is checked against the tool's schema. If the API returns a missing bioactivity field, the framework throws a validation error.

Absolutely. Pydantic AI is model-agnostic. You can query the EPA endpoints using a local open-source model while maintaining full type safety.

Use `MCPToolset`. The older `MCPServerHTTP` method is deprecated in Pydantic AI. The new toolset approach handles the unified Streamable HTTP connection.

The server processes raw chemical names, CASRNs, and DTXSIDs to fetch the corresponding toxicological data. Vinkius isolates this execution in a zero-trust V8 environment. The sandbox is destroyed the millisecond the HTTP request completes, leaving zero persistent storage or logs.

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