---

name: scp-oceangraph description: Use when you need to connect to the SciGraph SCP server for OceanGraph (Historical Marine Biodiversity Knowledge Graph / OceanGraphRAG KG built with Microsoft GraphRAG) 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.

SCP-OceanGraph (SciGraph) MCP client

What this SCP is

OceanGraph (Historical Marine Biodiversity Knowledge Graph, a.k.a. OceanGraphRAG KG) is a domain knowledge graph for historical marine biodiversity records. The page describes it as developed by Gustavo Marcelo Núñez (independent researcher) and built using Microsoft’s GraphRAG framework to digitize and structure mid-20th-century South American (especially Argentine) literature about marine mammals, seabirds, and resource utilization, enabling natural-language retrieval and analysis.

Connection info

• MCP server URL:
  • https://scp.intern-ai.org.cn/api/v1/mcp/37/SciGraph
• Auth header:
  • SCP-HUB-API-KEY: {API-KEY}

Install

pip install mcp

Configure (MCP config JSON)

{
  "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}"
      }
    }
  }
}

Tools

query_cypher

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 (OceanGraph):

{
  "cypher": "MATCH (e:Experiment:OceanGraph) RETURN e.id as experiment_id",
  "kg_name": "OceanGraph",
  "limit": 5
}

get_kg_statistics

Return graph statistics.

Example arguments:

{ "kg_name": "OceanGraph" }

get_entity_details

Return entity details.

Example arguments:

{ "entity_identifier": "experiment_1", "kg_name": "OceanGraph" }

get_experiment_workflow

Return the full workflow of an experiment.

Example arguments:

{ "experiment_id": "experiment_1" }

Python example (streamable HTTP)

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 OceanGraph
    result = await session.call_tool(
        "get_kg_statistics",
        arguments={"kg_name": "OceanGraph"},
    )
    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())

Citation

Nuñez, G., Zárate, M., Ceballos, D., & Fillottrani, P. (2025). Digitizing and Structuring Early Marine Biodiversity Records: A GraphRAG-Based Methodology. The 1st GOBLIN Workshop on Knowledge Graph Technologies (GOBLIN25), Leipzig, Germany. Zenodo. https://doi.org/10.5281/zenodo.16912811

Reference

For the full scraped page text, read:

• references/source.md