drugsda-file-transfer

Implement data transmission between the local computer and the MCP Server using Base64 encoding

Best use case

drugsda-file-transfer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Implement data transmission between the local computer and the MCP Server using Base64 encoding

Teams using drugsda-file-transfer should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/drugsda-file-transfer/SKILL.md --create-dirs "https://raw.githubusercontent.com/SpectrAI-Initiative/InnoClaw/main/.claude/skills/drugsda-file-transfer/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/drugsda-file-transfer/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How drugsda-file-transfer Compares

Feature / Agentdrugsda-file-transferStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Implement data transmission between the local computer and the MCP Server using Base64 encoding

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# File Transfer

## Usage

### 1. MCP Server Definition

```python
import json
from contextlib import AsyncExitStack
from mcp.client.streamable_http import streamablehttp_client
from mcp import ClientSession

class DrugSDAClient:    
    def __init__(self, server_url: str):
        self.server_url = server_url
        self.session = None
        
    async def connect(self):
        print(f"server url: {self.server_url}")
        try:
            self.transport = streamablehttp_client(
                url=self.server_url,
                headers={"SCP-HUB-API-KEY": "sk-a0033dde-b3cd-413b-adbe-980bc78d6126"}
            )
            self._stack = AsyncExitStack()
            await self._stack.__aenter__()
            self.read, self.write, self.get_session_id = await self._stack.enter_async_context(self.transport)
            
            self.session_ctx = ClientSession(self.read, self.write)
            self.session = await self._stack.enter_async_context(self.session_ctx)

            await self.session.initialize()
            session_id = self.get_session_id()
            
            print(f"✓ connect success")
            return True
            
        except Exception as e:
            print(f"✗ connect failure: {e}")
            import traceback
            traceback.print_exc()
            return False
    
    async def disconnect(self):
        """Disconnect from server"""
        try:
            if hasattr(self, '_stack'):
                await self._stack.aclose()
            print("✓ already disconnect")
        except Exception as e:
            print(f"✗ disconnect error: {e}")
    def parse_result(self, result):
        try:
            if hasattr(result, 'content') and result.content:
                content = result.content[0]
                if hasattr(content, 'text'):
                    return json.loads(content.text)
            return str(result)
        except Exception as e:
            return {"error": f"parse error: {e}", "raw": str(result)}
```

### 2. Transfer local file to MCP server

Example code:

```python
import base64

client = DrugSDAClient("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool")
if not await client.connect():
    print("connection failed")
    return

## Convert local file to base64 string
local_file = "/path/a.txt"		#Input local file path
with open(local_file, "rb") as f:
    file_content = f.read()
    file_base64_string = base64.b64encode(file_content).decode('utf-8')

## Call tool base64_to_server_file to save base64 string as server file
response = await client.session.call_tool(
    "base64_to_server_file",
    arguments={
        "file_name": "a.txt",
        "file_base64_string": file_base64_string
    }
)
result = client.parse_result(response)
save_file = result["save_file"]	#Server file path after transfer	

await client.disconnect() 
```

### 3. Transfer MCP server file to local

Example code:

```python
import base64

client = DrugSDAClient("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool")
if not await client.connect():
    print("connection failed")
    return

## Call tool server_file_to_base64 to convert server file to base64 string
response = await client.session.call_tool(
    "server_file_to_base64",
    arguments={
        "file_path": "/path/a.txt" 	#Input server file path
    }
)
result = client.parse_result(response)
base64_string = result["base64_string"]
file_name = result["file_name"]

## Convert base64 string to local file
file_data = base64.b64decode(base64_string)    
local_file_path = "/path/" + file_name
with open(local_file_path, "wb") as f:
    f.write(file_data)

await client.disconnect()
```

Related Skills

pharmacokinetics_profile

370
from SpectrAI-Initiative/InnoClaw

Pharmacokinetics Profile Builder - Build a PK profile: FDA pharmacokinetics, clinical pharmacology, dosage info, and molecular properties. Use this skill for pharmacology tasks involving get pharmacokinetics by drug name get clinical pharmacology by drug name get dosage and storage information by drug name get compound by name. Combines 4 tools from 2 SCP server(s).

drugsda-target-retrieve

370
from SpectrAI-Initiative/InnoClaw

Search the protein information from the input gene name and downloads the optimal PDB or AlphaFold structures.

drugsda-rgroup-sampling

370
from SpectrAI-Initiative/InnoClaw

Generate new molecules sampling from the input scaffold.

drugsda-prosst

370
from SpectrAI-Initiative/InnoClaw

Given a protein sequence and its structure, employ ProSST model to predict mutation effects and obtain the top-k mutated sequences.

drugsda-peptide-sampling

370
from SpectrAI-Initiative/InnoClaw

Generate new peptide molecules sampling from the input peptide sequence.

drugsda-p2rank

370
from SpectrAI-Initiative/InnoClaw

No description provided.

drugsda-mol2mol-sampling

370
from SpectrAI-Initiative/InnoClaw

Generate new molecules sampling from the input molecule.

drugsda-mol-similarity

370
from SpectrAI-Initiative/InnoClaw

Compute the Tanimoto similarities between a target molecule and a list of candidate molecules using Morgan fingerprints.

drugsda-mol-properties

370
from SpectrAI-Initiative/InnoClaw

Calculate different types of molecular properties based on SMILES strings, covering basic physicochemical properties, hydrophobicity, hydrogen bonding capability, molecular complexity, topological structures, charge distribution, and custom complexity metrics, respectively.

drugsda-linker-sampling

370
from SpectrAI-Initiative/InnoClaw

Generate new molecules sampling from the input two warhead fragments.

drugsda-esmfold

370
from SpectrAI-Initiative/InnoClaw

Use ESMFold model to predict 3D structure of the input protein sequence.

drugsda-drug-likeness

370
from SpectrAI-Initiative/InnoClaw

Compute the drug-likeness metrics (QED score and Number of violations of Lipinski's Rule of Five) of the input candidate molecules (SMILES format).