Use when you need to connect to the SciGraph SCP server for Theoria (curated theoretical physics knowledge graph with JSON entries containing equations, derivations, assumptions, references, and verification code) and call its MCP tools (query_cypher, get_kg_statistics, get_entity_details, get_experiment_workflow), including streamableHttp configuration with SCP-HUB-API-KEY and Python 3.10+ usage examples.
Theoria is a curated theoretical physics knowledge graph derived from structured JSON entries. Each entry represents a theoretical result and includes equations, definitions, derivation steps, assumptions, references, contributors, and programmatic verification code.
https://scp.intern-ai.org.cn/api/v1/mcp/37/SciGraphSCP-HUB-API-KEY: {API-KEY}pip install mcp
{
"mcpServers": {
"SciGraph": {
"type": "streamableHttp",
"description": "这是一款面向科学研究的统一知识查询服务,集成了化学、生物等多个学科领域的知识图谱数据,支持跨学科知识检索、实体关系查询、领域知识问答等操作",
"url": "https://scp.intern-ai.org.cn/api/v1/mcp/37/SciGraph",
"headers": {
"SCP-HUB-API-KEY": "{API-KEY}"
}
}
}
}
Execute a Cypher query and return JSON results.
Arguments:
cypher (string, required)kg_name (string|null, optional, default null)limit (int, optional, default 100)Example arguments (Theoria):
{
"cypher": "MATCH (e:Experiment:Theoria) RETURN e.id as experiment_id",
"kg_name": "Theoria",
"limit": 5
}
Return graph statistics.
Example arguments:
{ "kg_name": "Theoria" }
Return entity details.
Example arguments:
{ "entity_identifier": "experiment_1", "kg_name": "Theoria" }
Return the full workflow of an experiment.
Example arguments:
{ "experiment_id": "experiment_1" }
import asyncio
import json
from mcp.client.streamable_http import streamablehttp_client
from mcp.client.session import ClientSession
SERVER_URL = "https://scp.intern-ai.org.cn/api/v1/mcp/37/SciGraph"
async def main():
transport = streamablehttp_client(
url=SERVER_URL,
headers={"SCP-HUB-API-KEY": "sk-xxx"},
)
read, write, get_session_id = await transport.__aenter__()
session_ctx = ClientSession(read, write)
session = await session_ctx.__aenter__()
await session.initialize()
# Example: stats for Theoria
result = await session.call_tool(
"get_kg_statistics",
arguments={"kg_name": "Theoria"},
)
data = json.loads(result.content[0].text)
print(data)
await session_ctx.__aexit__(None, None, None)
await transport.__aexit__(None, None, None)
if __name__ == "__main__":
asyncio.run(main())
For the full scraped page text, read:
references/source.md