Getting started（入门指南）

Use the following section below to explore useful tips and best practices to get started with Palantir MCP.

Ask for coding help

If you need coding assistance, the Palantir MCP can help by searching the Palantir documentation or getting context about your current repository.

In a TypeScript OSDK repository:

What ontology objects do I have in my OSDK?

In a Python transforms repository:

Can you rewrite this Python transform to use lightweight?

Analyze a dataset

If you are working in a Python transforms repository, it is often necessary to understand the contents of a dataset. You can prompt the model to analyze datasets for you by providing a dataset RID.

Replace the in the prompt below with a dataset RID or URL to the dataset, or reference an existing transform code file (commonly using the @ shortcut).

Can you find an appropriate primary key in this dataset: <RID>?

Create an Ontology object with notional data

If you are working on a TypeScript OSDK application, it is common to reference data that may not yet be in the ontology. Instead of breaking focus on your current task, you can ask the MCP to create notional data for you and continue working on your application.

I'm working on this OSDK application and need to reference some user data that I don't have in my OSDK yet.
Can you create a new notional user dataset, create a new User Ontology object, and then create a pull request for me?

The user dataset should have the columns:
user_id, name, email

Ask what tools are available

To receive a full list of tools available in Palantir MCP that can be useful for your workflows, you can ask the following:

What tools does the Palantir MCP (Model Context Protocol) provide?
When should they be used?

---

中文翻译

---

入门指南

请参考以下章节，探索使用 Palantir MCP 的实用技巧和最佳实践。

寻求编码帮助

如需编码协助，Palantir MCP 可通过搜索 Palantir 文档或获取当前仓库的上下文信息来提供帮助。

在 TypeScript OSDK 仓库中：

我的 OSDK 中有哪些本体对象（ontology objects）？

在 Python transforms 仓库中：

能否将此 Python transform 重写为 lightweight 版本？

分析数据集

若在 Python transforms 仓库中工作，通常需要了解数据集的内容。您可以通过提供数据集 RID，提示模型为您分析数据集。

将下方提示中的 替换为数据集 RID 或数据集 URL，或引用现有的 transform 代码文件（通常使用 @ 快捷键）。

能否在此数据集中找到合适的主键（primary key）：<RID>？

使用模拟数据创建本体对象

若在 TypeScript OSDK 应用上工作，常需引用尚未纳入本体的数据。您无需中断当前任务，可要求 MCP 为您创建模拟数据，继续开发应用。

我正在开发此 OSDK 应用，需要引用一些尚未在 OSDK 中的用户数据。
能否为我创建一个新的模拟用户数据集，创建一个新的用户本体对象（User Ontology object），然后生成一个拉取请求（pull request）？

用户数据集应包含以下列：
user_id, name, email

查询可用工具

如需获取 Palantir MCP 中可用于工作流程的完整工具列表，可提出以下问题：

Palantir MCP（模型上下文协议，Model Context Protocol）提供了哪些工具？
这些工具应在何时使用？