Phenotype Retrieval by HPO ID

SkillDev tools

Retrieve phenotype information from Monarch Initiative using HPO (Human Phenotype Ontology) IDs to understand disease manifestations.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Phenotype Retrieval by HPO ID skill

What this skill tells your AI

The instructions your AI receives, as published by internscience/scp in skills/phenotype-by-hpo-id/SKILL.md and read by ahel’s review.

Usage

1. MCP Server Definition

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

class OrigeneClient:
    """Origene-Monarch MCP Client"""

    def __init__(self, server_url: str, api_key: str):
        self.server_url = server_url
        self.api_key = api_key
        self.session = None

    async def connect(self):
        try:
            self.transport = streamablehttp_client(
                url=self.server_url,
                headers={"SCP-HUB-API-KEY": self.api_key}
            )
            self.read, self.write, self.get_session_id = await self.transport.__aenter__()
            self.session_ctx = ClientSession(self.read, self.write)
            self.session = await self.session_ctx.__aenter__()
            await self.session.initialize()
            return True
        except Exception as e:
            print(f"✗ connect failure: {e}")
            return False

    async def disconnect(self):
        try:
            if self.session:
                await self.session_ctx.__aexit__(None, None, None)
            if hasattr(self, 'transport'):
                await self.transport.__aexit__(None, None, None)
        except Exception as e:
            print(f"✗ disconnect error: {e}")

    def parse_result(self, result):
        if isinstance(result, dict):
            content_list = result.get("content") or []
        else:
            content_list = getattr(result, "content", []) or []
        texts = []
        for item in content_list:
            if isinstance(item, dict):
                if item.get("type") == "text":
                    texts.append(item.get("text") or "")
            else:
                if getattr(item, "type", None) == "text":
                    texts.append(getattr(item, "text", "") or "")
        return "".join(texts)

2. Phenotype Retrieval Workflow

Implementation:

## Initialize client
client = OrigeneClient(
    "https://scp.intern-ai.org.cn/api/v1/mcp/16/Origene-Monarch",
    "<your-api-key>"
)

if not await client.connect():
    print("connection failed")
    exit()

## Retrieve phenotype by HPO ID
result = await client.session.call_tool(
    "get_phenotype_by_HPO_ID",
    arguments={
        "id": "HP:0001250"  # Seizure
    }
)

result_data = client.parse_result(result)
print(result_data)

await client.disconnect()

Tool Descriptions

Origene-Monarch Server:

  • get_phenotype_by_HPO_ID: Retrieve phenotype information
    • Args:
      • id (str): HPO ID (e.g., "HP:0001250")
    • Returns: Phenotype description, associated genes, and diseases

Use Cases

  • Clinical diagnosis support
  • Genetic disorder characterization
  • Phenotype-driven gene discovery
  • Rare disease research

Signals

GitHub stars
167
Forks
9
Last commit
Jun 2026
Advanced
Catalog kind
skill
Gateway key
phenotype-by-hpo-id
Source
github.com/internscience/scp