How to Use the EPA Computational Toxicology MCP in OpenAI Agents SDK

Q: How do I connect EPA Computational Toxicology to the OpenAI Agents SDK?

Install the openai-agents package. Setup MCPServerStreamableHttp pointing to your Vinkius MCP endpoint. Pass it to the Agent constructor via the mcpservers array.

Q: Can the OpenAI Agents SDK cache EPA Computational Toxicology queries?

Yes. Set cacheToolsList=True when initializing the server. This stops the agent from re-fetching the tool schemas on every single CASRN lookup.

Build production-grade chemical screening agents with the OpenAI Agents SDK and EPA CompTox data.

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 OpenAI Agents SDK

Create your Vinkius account to connect EPA Computational Toxicology to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve Chemical Identifiers

`search_chemical_by_casrn` and `search_chemical_by_name` let your OpenAI agents map raw identifiers to exact DTXSIDs. You hand the agent a messy list of industrial solvents. It hits the EPA database, resolves the synonyms, and locks down the exact chemical identities before passing the context to a specialized hazard-evaluation agent. Handoffs matter here. One agent handles the initial identifier resolution using `get_chemical_synonyms`. It then routes the validated DTXSID to a separate risk-assessment agent that pulls in regulatory lists via `get_chemical_lists`. The OpenAI guardrails ensure the agent never hallucinates a CAS registry number during the workflow.

Run Toxicity Checks via MCP Server

`get_hazard_summary` and `get_bioactivity_summary` pull high-throughput ToxCast screening results straight into your agent's context window. Your AI client doesn't guess if a compound causes endocrine disruption. It reads the actual ToxValDB hazard assessment data directly from the source. You configure this in Python using `MCPServerStreamableHttp` with `cacheToolsList=True` for speed. The agent executes the tools, evaluates the bioactivity thresholds, and logs the entire decision chain in your OpenAI dashboard tracing. If the toxicity exceeds your safety parameters, the agent halts the process.

Analyze Environmental Fate

`get_exposure_summary` and `get_fate_and_transport` feed predicted environmental half-life and product use data to your agents. You need to know if a chemical persists in municipal water. The agent queries the ExpoCast data through the MCP server and retrieves the exact bioconcentration metrics. Combine this with `get_physicochemical_properties`. The agent checks the experimental melting point and logP values to build a complete environmental profile. Since the OpenAI Agents SDK auto-discovers these tools, you just pass the server to your agent constructor and let it run the queries.

Setup guide

Set up EPA Computational Toxicology MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all EPA Computational Toxicology tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives EPA Computational Toxicology tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate EPA Computational Toxicology tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="EPA Computational Toxicology Agent",
            instructions="You have access to EPA Computational Toxicology tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the `openai-agents` package. Setup `MCPServerStreamableHttp` pointing to your Vinkius MCP endpoint. Pass it to the Agent constructor via the `mcp_servers` array.

Yes. Set `cacheToolsList=True` when initializing the server. This stops the agent from re-fetching the tool schemas on every single CASRN lookup.

The agent catches the error. You can build guardrails in the OpenAI Agents SDK to retry with `search_chemical_by_name` if `search_chemical_by_casrn` returns a blank.

No. Vinkius handles the upstream authentication. You only need your single endpoint token to authenticate the connection.

The server processes CASRNs, chemical names, and DTXSIDs. If you search for an unlisted proprietary analog, that query string hits the EPA public endpoints. Vinkius runs this in a zero-trust V8 Isolate that destroys the session immediately after the query resolves, leaving no logs behind.

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