How to Use the EPA Computational Toxicology MCP in LangChain

Q: How does the EPA Computational Toxicology server handle multi-server aggregation in LangChain?

You initialize the MultiServerMCPClient with the Vinkius endpoint. This lets your agent combine chemical data with other tools, like a patent search database. The agent coordinates calls across all connected servers to compile a complete chemical profile.

Q: What happens if a CASRN search returns multiple synonyms?

Your agent calls getchemicalsynonyms to resolve any naming conflicts. This tool returns all registered alternative names for that specific substance. The agent then selects the primary IUPAC name to maintain clean database records.

Build multi-step chemical safety reasoning chains in LangChain with live EPA CompTox toxicity, hazard, and exposure 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 LangChain

Create your Vinkius account to connect EPA Computational Toxicology to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain EPA hazard evaluations inside LangChain

This MCP Server connects LangChain directly to the EPA CompTox database for automated chemical search and hazard profiling. First, your agent runs `search_chemical_by_name` to get the DTXSID. Then, it feeds that exact identifier into `get_hazard_summary` to pull toxicity thresholds instantly. This setup removes manual copying between tools. You get a clean, traceable pipeline where the output of your chemical search feeds the next analytical step. Every chemical tool call transition is logged in LangSmith so you verify the analytical logic.

Map environmental fate and exposure pathways

This MCP Server provides your LangChain agent with environmental fate and exposure models. By calling `get_fate_and_transport`, your agent pulls bioconcentration factors and half-lives. It pairs this data with `get_exposure_summary` to estimate real-world product usage and exposure levels. You do not need to hardcode these chemical data transitions in LangChain. The LangChain agent evaluates the physical constants and decides if the exposure risk warrants further screening. It runs these complex chemical evaluations in seconds, keeping your regulatory pipeline moving.

Audit regulatory lists and bioactivity profiles

This MCP Server gives your LangChain pipelines direct access to regulatory watchlists and biological assay results. Your agent invokes `get_chemical_lists` to cross-reference the compound against international watchlists. It immediately backs this up by querying `get_bioactivity_summary` to check high-throughput screening assays. Having this data inside your active context lets you flag bad actors early in the design phase. You avoid wasting resources on chemicals destined for regulatory bans. It is a fast, programmatic way to screen candidates before ordering physical lab tests.

Setup guide

Set up EPA Computational Toxicology MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes EPA Computational Toxicology tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "epa-computational-toxicology-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent EPA Computational Toxicology transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You use the LangChain MCP adapter to convert the server tools into runnable tools. When `search_chemical_by_casrn` finds a chemical, the agent extracts the DTXSID from the JSON output. It then feeds that ID directly into `get_physicochemical_properties` in the next link of your chain.

Yes, every tool call is fully observable. You track exactly how long `get_bioactivity_summary` takes to return data. LangSmith captures the raw inputs and outputs for every single chemical query you run.

You initialize the `MultiServerMCPClient` with the Vinkius endpoint. This lets your agent combine chemical data with other tools, like a patent search database. The agent coordinates calls across all connected servers to compile a complete chemical profile.

Your agent calls `get_chemical_synonyms` to resolve any naming conflicts. This tool returns all registered alternative names for that specific substance. The agent then selects the primary IUPAC name to maintain clean database records.

Vinkius runs this MCP Server in an isolated, zero-trust V8 sandbox. Your CASRNs, chemical names, and toxicity queries are processed ephemerally and never stored. No one else sees the structures or compounds you are researching.

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