Ontology MCP (OMCP)¶
Ontology MCP (OMCP) is a Developer Console feature that exposes your application's ontology resources as Model Context Protocol (MCP) tools. This enables AI agents and external systems to interact with your ontology as MCP clients.
What is Ontology MCP?¶
Ontology MCP makes your application's ontology resources (such as object types, action types, and query functions) available as MCP tools. External AI agents can then discover and use these tools to read objects, execute actions, and query data from your ontology.
The Model Context Protocol ↗ is an open standard that enables AI systems to securely connect to external data sources and tools. By enabling Ontology MCP, your application becomes an MCP server that AI agents can connect to as MCP clients.
Ontology MCP vs. Palantir MCP¶
Ontology MCP and Palantir MCP serve different purposes:
-
Ontology MCP (OMCP) is designed for ontology consumers: external AI agents that need to safely write data to your ontology. Ontology MCP allows LLM agents to read objects, execute predefined actions, and query data, while restricting which actions the agent can take through application restrictions. This makes it safe for external agents to interact with production ontology data.
-
Palantir MCP is designed for ontology builders, such as developers working with OSDK applications, datasets, transforms, and ontology development. Palantir MCP provides 70+ tools for building and modifying ontology types (object types, link types, action types), but cannot write actual ontology data. Palantir MCP focuses on development workflows, not production data interaction.
In summary: Ontology MCP enables controlled writes to ontology data, while Palantir MCP enables modifications to ontology structure.
LLM disclaimer¶
:::callout{theme="warning"} By enabling Ontology MCP on your local device with LLMs hosted outside of Palantir AIP, you are making data in your Palantir environment available to an external MCP client. Ensure that this action is compliant with your organization's policies. :::
When using Ontology MCP with external AI systems, consider the following:
- Review your organization's data governance and compliance policies before enabling Ontology MCP.
- Ensure that the ontology resources exposed through MCP comply with your data security requirements.
- Use application restrictions and permissions to restrict access to sensitive resources.
中文翻译¶
Ontology MCP (OMCP)¶
Ontology MCP（OMCP）是 Developer Console 的一项功能，可将应用程序的本体资源以 Model Context Protocol（MCP）工具的形式对外暴露。这使得 AI 代理和外部系统能够作为 MCP 客户端与您的本体进行交互。
什么是 Ontology MCP？¶
Ontology MCP 将应用程序的本体资源（如对象类型、操作类型和查询函数）作为 MCP 工具提供。外部 AI 代理可以发现并使用这些工具来读取对象、执行操作以及从本体中查询数据。
Model Context Protocol ↗ 是一项开放标准，使 AI 系统能够安全地连接到外部数据源和工具。启用 Ontology MCP 后，您的应用程序将成为 MCP 服务器，AI 代理可作为 MCP 客户端与之连接。
Ontology MCP 与 Palantir MCP 的区别¶
Ontology MCP 和 Palantir MCP 服务于不同的目的：
-
Ontology MCP（OMCP） 专为本体消费者设计：即需要安全地向本体写入数据的外部 AI 代理。Ontology MCP 允许 LLM 代理读取对象、执行预定义操作和查询数据，同时通过应用程序限制限制代理可执行的操作。这使得外部代理能够安全地与生产环境的本体数据进行交互。
-
Palantir MCP 专为本体构建者设计：例如使用 OSDK 应用程序、数据集、转换和本体开发的开发者。Palantir MCP 提供 70 多种工具，用于构建和修改本体类型（对象类型、链接类型、操作类型），但无法写入实际的本体数据。Palantir MCP 侧重于开发工作流，而非生产数据交互。
总结：Ontology MCP 支持对本体数据的受控写入，而 Palantir MCP 支持对本体结构的修改。
LLM 免责声明¶
:::callout{theme="warning"} 在本地设备上启用 Ontology MCP 并使用 Palantir AIP 外部的 LLM 时，您将把 Palantir 环境中的数据提供给外部 MCP 客户端。请确保此操作符合您组织的政策。 :::
将 Ontology MCP 与外部 AI 系统配合使用时，请注意以下事项：