OSDU MCP Server

OSDU MCP Server

AI-powered access to OSDU subsurface data through natural language, enabling AI assistants to interact with the OSDU platform via conversational interfaces for search, schema management, records, and compliance.

Category
访问服务器

README

OSDU MCP Server

CI Release Python License MCP

AI-powered access to OSDU subsurface data through natural language.

Enable AI assistants to interact with the OSDU (Open Subsurface Data Universe) platform through conversational interfaces. Search data, manage schemas, handle records, and maintain compliance—all through natural language.

Why OSDU MCP Server?

Transform complex OSDU API workflows into simple conversations:

Before:

curl -X POST https://osdu.com/api/search/v2/query \
  -H "Authorization: Bearer $TOKEN" \
  -d '{"kind":"osdu:wks:master-data--Well:*"}'
# ... parse JSON, check schemas, format records, handle ACLs ...

After:

You: "Find all wells in the North Sea and show their schemas"
AI: ✅ Found 247 wells
    📋 Retrieved schema requirements
    🎯 Ready to work with the data

Key Features

Feature Description
Natural Language Complex API calls and Elasticsearch queries through conversation
Multi-Cloud Auth Azure, AWS, and GCP with zero-config credential discovery
31 MCP Tools Complete OSDU API coverage (storage, search, schema, legal, partition)
Template-Driven Pre-built templates eliminate format-guessing errors
Safety Controls Write/delete protection, confirmation requirements, audit logging
Resources & Prompts Guided workflows and interactive examples

Quick Start

Setup

Install with UV in VS Code

mcp add osdu-mcp-server -- uvx osdu-mcp-server \
  -e OSDU_MCP_SERVER_URL=https://your-osdu.com \
  -e OSDU_MCP_SERVER_DATA_PARTITION=opendes \
  -e AZURE_CLIENT_ID=your-client-id \
  -e AZURE_TENANT_ID=your-tenant-id

Or add manually to your MCP configuration:

{
  "mcpServers": {
    "osdu-mcp-server": {
      "command": "uvx",
      "args": ["osdu-mcp-server"],
      "env": {
        "OSDU_MCP_SERVER_URL": "https://your-osdu.com",
        "OSDU_MCP_SERVER_DATA_PARTITION": "opendes",
        "AZURE_CLIENT_ID": "your-client-id",
        "AZURE_TENANT_ID": "your-tenant-id"
      }
    }
  }
}

Note: Authentication credentials (Azure/AWS/GCP) are auto-discovered from your environment. See Getting Started for all auth methods.

Try It

"Check the health of my OSDU platform"

"List all schemas available in the system"

"Find wells in the North Sea region"

"Show me the legal tag template"

What's Included

31 Tools across 6 OSDU services:

  • Core - Health checks and user entitlements
  • Partition - List, get, create, update, and delete partitions
  • Legal - Complete legal tag management with search and batch operations
  • Schema - Schema discovery, search, and management
  • Search - Elasticsearch queries and record discovery
  • Storage - Full CRUD operations with versioning and batch support

3 Prompts for guided workflows:

  • Capability overview and quick start
  • Search pattern guidance with Elasticsearch examples
  • Complete record lifecycle workflows

4 Resources with working templates:

  • Legal tag templates
  • Record structure examples
  • ACL format patterns
  • Search query patterns

Configuration

Required

  • OSDU_MCP_SERVER_URL - Your OSDU platform URL
  • OSDU_MCP_SERVER_DATA_PARTITION - Data partition ID

Optional

  • OSDU_MCP_SERVER_DOMAIN - Data domain for ACLs (default: contoso.com)
  • OSDU_MCP_ENABLE_WRITE_MODE - Enable create/update (default: false)
  • OSDU_MCP_ENABLE_DELETE_MODE - Enable delete/purge (default: false)

License

Apache License 2.0 - see LICENSE for details.


<div align="center">

Getting StartedAuthenticationArchitectureContributing

</div>

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选