How to Use the EPA Computational Toxicology MCP in Google ADK

Q: How do I configure EPA Computational Toxicology with Google ADK?

Install google-adk. Initialize an McpToolset using StreamableHttpServerParameters with your Vinkius MCP URL. Pass the toolset to your LlmAgent.

Q: Can Google ADK filter the EPA Computational Toxicology tools?

Yes. Use the toolnames argument. You can restrict an agent to only use getphysicochemicalproperties if you want to block it from pulling hazard summaries.

Feed EPA chemical hazard data directly into Gemini's massive context window using Google ADK.

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 Google ADK

Create your Vinkius account to connect EPA Computational Toxicology to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map CAS Numbers in Google ADK

`search_chemical_by_casrn` and `get_chemical_details` let your Gemini agents pull exact structural metadata from the EPA database. You dump thousands of chemical registry numbers from your BigQuery tables into the agent. It maps them all to DTXSIDs in a single pass. Gemini's 1M+ token context window changes how you handle this data. Instead of chunking queries, your AI client pulls the structural details for entire chemical classes at once. You configure an `McpToolset` with your Vinkius MCP server URL and pass it straight into the `LlmAgent`.

Extract Persistence Metrics

`get_fate_and_transport` and `get_exposure_summary` extract environmental persistence and predicted human exposure levels. Your agent reads the ExpoCast data to determine if an industrial solvent will bioaccumulate in local watersheds. This integrates heavily with Google Cloud infrastructure. Your agent grabs the half-life data from the MCP server and cross-references it against historical environmental monitoring data stored in Vertex AI. You get actual regulatory risk profiles based on hard data, not LLM guesses.

Retrieve ToxCast Screening Results

`get_bioactivity_summary` and `get_hazard_summary` deliver raw ToxCast screening results and ToxValDB metrics. The agent pulls the high-throughput in vitro assay results to flag potential endocrine disruptors before physical testing begins. You can filter these endpoints using the `tool_names` parameter in Google ADK. If your specific agent only needs toxicity data, you restrict its access. It pulls the bioactivity thresholds, formats the results, and writes the safety summary back to your enterprise data warehouse.

Setup guide

Set up EPA Computational Toxicology MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with EPA Computational Toxicology tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="EPA Computational Toxicology_agent",
    model="gemini-2.0-flash",
    instruction="You have access to EPA Computational Toxicology tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk`. Initialize an `McpToolset` using `StreamableHttpServerParameters` with your Vinkius MCP URL. Pass the toolset to your `LlmAgent`.

Yes. Use the `tool_names` argument. You can restrict an agent to only use `get_physicochemical_properties` if you want to block it from pulling hazard summaries.

Rarely. Even pulling full toxicity profiles for dozens of chemicals barely dents the 1M+ token limit. Your Gemini agent can hold massive amounts of ToxCast data simultaneously.

No. The server handles the upstream request pacing. Your agent just sends the queries and waits for the response.

The server only sees the specific chemical identifiers, like IUPAC names or CASRNs, that your agent explicitly sends to the tools. Vinkius executes these requests in an ephemeral sandbox. The connection drops immediately after the data returns, and no query history is retained.

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