substance-toxicology

name: substance_toxicology description: "Substance Toxicology Report - Toxicology report: PubChem substance data, FDA toxicology, carcinogenicity data, and environmental warnings. Use this skill for toxicology tasks involving get substance by name get nonclinical toxicology info by drug name get carcinogenic mutagenic fertility impairment info by drug name get environmental warning by drug name. Combines 4 tools from 2 SCP server(s)."

Substance Toxicology Report

Discipline: Toxicology | Tools Used: 4 | Servers: 2

Description

Toxicology report: PubChem substance data, FDA toxicology, carcinogenicity data, and environmental warnings.

Tools Used

• get_substance_by_name from pubchem-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/8/Origene-PubChem
• get_nonclinical_toxicology_info_by_drug_name from fda-drug-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug
• get_carcinogenic_mutagenic_fertility_impairment_info_by_drug_name from fda-drug-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug
• get_environmental_warning_by_drug_name from fda-drug-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug

Workflow

1. Get PubChem substance data
2. Get FDA nonclinical toxicology
3. Get carcinogenicity data
4. Get environmental warnings

Test Case

Input

{
    "substance": "benzene",
    "drug_name": "benzene"
}

Expected Steps

1. Get PubChem substance data
2. Get FDA nonclinical toxicology
3. Get carcinogenicity data
4. Get environmental warnings

Usage Example

Note: Replace <YOUR_SCP_HUB_API_KEY> with your own SCP Hub API Key. You can obtain one from the SCP Platform.

import asyncio
import json
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
from mcp.client.sse import sse_client

SERVERS = {
    "pubchem-server": "https://scp.intern-ai.org.cn/api/v1/mcp/8/Origene-PubChem",
    "fda-drug-server": "https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug"
}

async def connect(url, transport_type):
    transport = streamablehttp_client(url=url, headers={"SCP-HUB-API-KEY": "<YOUR_SCP_HUB_API_KEY>"})
    read, write, _ = await transport.__aenter__()
    ctx = ClientSession(read, write)
    session = await ctx.__aenter__()
    await session.initialize()
    return session, ctx, transport

def parse(result):
    try:
        if hasattr(result, 'content') and result.content:
            c = result.content[0]
            if hasattr(c, 'text'):
                try: return json.loads(c.text)
                except: return c.text
        return str(result)
    except: return str(result)

async def main():
    # Connect to required servers
    sessions = {}
    sessions["pubchem-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/8/Origene-PubChem", "streamable-http")
    sessions["fda-drug-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug", "streamable-http")

    # Execute workflow steps
    # Step 1: Get PubChem substance data
    result_1 = await sessions["pubchem-server"].call_tool("get_substance_by_name", arguments={})
    data_1 = parse(result_1)
    print(f"Step 1 result: {json.dumps(data_1, indent=2, ensure_ascii=False)[:500]}")

    # Step 2: Get FDA nonclinical toxicology
    result_2 = await sessions["fda-drug-server"].call_tool("get_nonclinical_toxicology_info_by_drug_name", arguments={})
    data_2 = parse(result_2)
    print(f"Step 2 result: {json.dumps(data_2, indent=2, ensure_ascii=False)[:500]}")

    # Step 3: Get carcinogenicity data
    result_3 = await sessions["fda-drug-server"].call_tool("get_carcinogenic_mutagenic_fertility_impairment_info_by_drug_name", arguments={})
    data_3 = parse(result_3)
    print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")

    # Step 4: Get environmental warnings
    result_4 = await sessions["fda-drug-server"].call_tool("get_environmental_warning_by_drug_name", arguments={})
    data_4 = parse(result_4)
    print(f"Step 4 result: {json.dumps(data_4, indent=2, ensure_ascii=False)[:500]}")

    # Cleanup
    print("Workflow complete!")

if __name__ == "__main__":
    asyncio.run(main())