Revit MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_categoriesB | 获取 Revit 模型中的所有类别 |
| get_familiesC | 获取 Revit 模型中的所有族 |
| get_elementsC | 获取 Revit 模型中的元素 |
| get_levelsB | 获取 Revit 模型中的所有楼层 |
| get_viewsB | 获取 Revit 模型中的所有视图 |
| get_element_infoC | 获取 Revit 元素的详细信息 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| 当前 Revit 模型信息 | 提供当前打开的 Revit 模型的基本信息，包括名称、路径、版本和元素数量 |
TDQS
Scored across 6 tools
Every tool has a clearly distinct purpose targeting different Revit model components: categories, element info, elements, families, levels, and views. There is no overlap in functionality, and an agent can easily distinguish between them based on the specific resource each retrieves.
All tools follow a consistent verb_noun pattern with 'get_' as the prefix and a plural or singular noun describing the resource. This uniformity makes the tool set predictable and easy to navigate, with no deviations in naming style.
With 6 tools, the count is reasonable for a Revit model server, covering key retrieval operations. However, it might be slightly under-scoped as it lacks tools for creating, updating, or deleting elements, which could be expected in a full Revit integration.
The tool set is severely incomplete for a Revit domain, as it only provides read-only retrieval operations. There are significant gaps in CRUD coverage—no tools for creating, updating, or deleting elements, categories, families, etc., which will likely cause agent failures when trying to modify models.