Skill v1.0.0

currentAutomated scan100/100

internscience/scp/blast-protein-analysis

──Details

PublishedJune 16, 2026 at 11:16 PM

Content Hashsha256:5651ba34f7d68fb2...

Git SHAcea539856403

──Files

Files (1 file, 4.4 KB)

SKILL.md4.4 KBactive

SKILL.md · 115 lines · 4.4 KB

version: "1.0.0" name: blast_protein_analysis description: "BLAST & Protein Analysis Pipeline - BLAST search followed by comprehensive protein analysis: BLAST, then structure prediction, properties, and function. Use this skill for sequence bioinformatics tasks involving blast search pred protein structure esmfold calculate protein sequence properties predict protein function. Combines 4 tools from 4 SCP server(s)."

BLAST & Protein Analysis Pipeline

Discipline: Sequence Bioinformatics | Tools Used: 4 | Servers: 4

Description

BLAST search followed by comprehensive protein analysis: BLAST, then structure prediction, properties, and function.

Tools Used

`blast_search` from server-17 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/17/BioInfo-Tools
`pred_protein_structure_esmfold` from server-3 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model
`calculate_protein_sequence_properties` from server-2 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool
`predict_protein_function` from server-1 (sse) - https://scp.intern-ai.org.cn/api/v1/mcp/1/VenusFactory

Workflow

Run BLAST search
Predict structure for top hit
Calculate protein properties
Predict protein function

Test Case

Input

json

{
    "sequence": "MKTIIALSYIFCLVFA"
}

Expected Steps

Run BLAST search
Predict structure for top hit
Calculate protein properties
Predict protein function

Usage Example

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

python

import asyncio
import json
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
from mcp.client.sse import sse_client
SERVERS = {
    "server-17": "https://scp.intern-ai.org.cn/api/v1/mcp/17/BioInfo-Tools",
    "server-3": "https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model",
    "server-2": "https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool",
    "server-1": "https://scp.intern-ai.org.cn/api/v1/mcp/1/VenusFactory"
}
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["server-17"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/17/BioInfo-Tools", "streamable-http")
    sessions["server-3"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model", "streamable-http")
    sessions["server-2"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool", "streamable-http")
    sessions["server-1"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/1/VenusFactory", "sse")
    # Execute workflow steps
    # Step 1: Run BLAST search
    result_1 = await sessions["server-17"].call_tool("blast_search", arguments={})
    data_1 = parse(result_1)
    print(f"Step 1 result: {json.dumps(data_1, indent=2, ensure_ascii=False)[:500]}")
    # Step 2: Predict structure for top hit
    result_2 = await sessions["server-3"].call_tool("pred_protein_structure_esmfold", arguments={})
    data_2 = parse(result_2)
    print(f"Step 2 result: {json.dumps(data_2, indent=2, ensure_ascii=False)[:500]}")
    # Step 3: Calculate protein properties
    result_3 = await sessions["server-2"].call_tool("calculate_protein_sequence_properties", arguments={})
    data_3 = parse(result_3)
    print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")
    # Step 4: Predict protein function
    result_4 = await sessions["server-1"].call_tool("predict_protein_function", 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())

All versions