How to Use the EPA Computational Toxicology MCP in AutoGen

Q: How do I register EPA Computational Toxicology tools with AutoGen agents?

You use the mcpservertools function from the AutoGen extension. This automatically handles the schema conversion for tools like getphysicochemicalproperties. You then pass the mapped tools list directly to your agent's constructor.

Q: How does AutoGen handle schema conversion for the EPA Computational Toxicology MCP Server?

The McpToolAdapter in the AutoGen extension translates the server's tool schemas into the format AutoGen expects. This means tools like getchemicaldetails work out of the box. You do not need to write any manual wrapper code.

Deploy debating AutoGen agents to evaluate chemical safety, exposure, and regulatory lists using live 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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate chemical safety using this MCP Server

This MCP Server lets debating AutoGen agents query the EPA CompTox database during safety reviews. Complex chemical approvals require looking at data from multiple angles. In AutoGen, set up a toxicologist agent and a regulatory agent. One agent calls `get_hazard_summary` to analyze toxicity values, while the other runs `get_chemical_lists` to check for restrictions. These agents debate whether a chemical is safe to use in a new product. They challenge each other's interpretations of the data in real time. This collaborative process ensures your safety decisions are thoroughly vetted before you proceed.

Resolve chemical identity conflicts through multi-agent consensus

This MCP Server provides the critical chemical registries needed for AutoGen agents to resolve nomenclature conflicts. Chemical databases are messy, and synonyms often cause confusion. Your AutoGen agents coordinate to verify a compound's identity. One agent uses `search_chemical_by_name` to find the primary record, while another runs `search_chemical_by_casrn` to double-check the registry number. If the chemical names or registry numbers do not match up, the AutoGen agents discuss the discrepancy. They call `get_chemical_synonyms` to find the overlapping records. This automated cross-referencing guarantees your toxicological database remains clean and accurate.

Evaluate exposure and environmental fate concurrently

This MCP Server delivers environmental fate and consumer exposure metrics to your AutoGen agents. Assessing environmental impact involves balancing how a chemical behaves with where it is used. Deploy an environmental chemist agent to run `get_fate_and_transport` for half-life data. Simultaneously, an exposure analyst agent runs `get_exposure_summary` to check consumer use profiles. The agents combine these findings to estimate the overall environmental footprint. They negotiate on the risk level, matching persistence data against actual exposure vectors. You get a balanced, multi-perspective risk assessment without manual intervention.

Setup guide

Set up EPA Computational Toxicology MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes EPA Computational Toxicology tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="EPA Computational Toxicology_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent EPA Computational Toxicology data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="EPA Computational Toxicology_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent EPA Computational Toxicology data")
    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 AutoGen

You use the `mcp_server_tools` function from the AutoGen extension. This automatically handles the schema conversion for tools like `get_physicochemical_properties`. You then pass the mapped tools list directly to your agent's constructor.

Yes, the tools are shared across the conversation context. A toxicologist agent calls `get_bioactivity_summary`, and a safety agent immediately uses that output to run a hazard check. The shared conversation history keeps both agents aligned.

The `McpToolAdapter` in the AutoGen extension translates the server's tool schemas into the format AutoGen expects. This means tools like `get_chemical_details` work out of the box. You do not need to write any manual wrapper code.

The server supports both stdio and Streamable HTTP transports. For multi-agent systems running in distributed environments, Streamable HTTP is ideal. It lets your agents access the chemical database from separate microservices.

Vinkius processes all queries in secure, isolated V8 sandboxes. Your chemical names, CASRNs, and bioactivity queries are handled ephemerally. The data is never logged or used to train models, keeping your proprietary research safe.

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