SpectrAI-Initiative/organism_classification

Organism Classification & Database

Discipline: Taxonomy | Tools Used: 4 | Servers: 3

Description

Classify organism: NCBI taxonomy, Ensembl taxonomy, ChEMBL organisms, and genome info.

Tools Used

• get_taxonomy from ncbi-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI
• get_taxonomy_id from ensembl-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl
• get_organism_by_id from chembl-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL
• get_genome_dataset_report_by_taxon from ncbi-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI

Workflow

1. Get NCBI taxonomy
2. Get Ensembl taxonomy
3. Get ChEMBL organism info
4. Get genome dataset report

Test Case

Input

{
    "taxon": "9606",
    "species": "homo_sapiens"
}

Expected Steps

1. Get NCBI taxonomy
2. Get Ensembl taxonomy
3. Get ChEMBL organism info
4. Get genome dataset report

Usage Example

Note: Replace sk-b04409a1-b32b-4511-9aeb-22980abdc05c with your own SCP Hub API Key. You can obtain one from the SCP Platform.

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

SERVERS = {
    "ncbi-server": "https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI",
    "ensembl-server": "https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl",
    "chembl-server": "https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL"
}

async def connect(url, stack):
    transport = streamablehttp_client(url=url, headers={"SCP-HUB-API-KEY": "sk-b04409a1-b32b-4511-9aeb-22980abdc05c"})
    read, write, _ = await stack.enter_async_context(transport)
    ctx = ClientSession(read, write)
    session = await stack.enter_async_context(ctx)
    await session.initialize()
    return session

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():
    async with AsyncExitStack() as stack:
        # Connect to required servers
        sessions = {}
        sessions["ncbi-server"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI", stack)
        sessions["ensembl-server"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl", stack)
        sessions["chembl-server"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL", stack)

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

        # Step 2: Get Ensembl taxonomy
        result_2 = await sessions["ensembl-server"].call_tool("get_taxonomy_id", arguments={})
        data_2 = parse(result_2)
        print(f"Step 2 result: {json.dumps(data_2, indent=2, ensure_ascii=False)[:500]}")

        # Step 3: Get ChEMBL organism info
        result_3 = await sessions["chembl-server"].call_tool("get_organism_by_id", arguments={})
        data_3 = parse(result_3)
        print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")

        # Step 4: Get genome dataset report
        result_4 = await sessions["ncbi-server"].call_tool("get_genome_dataset_report_by_taxon", 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())