KR

kaitpw/rvt_docs_mcp

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

31 stars 6 forks 质量 43 趋势 11

一个MCP服务器,向大型语言模型展示Revit API文档和示例代码。

概览

由于 Revit API 的表面积极其庞大,AI 经常产生幻觉,比如类、方法、属性,甚至整个命名空间。此外,有用的但非官方或不常见的 API 用途非常小众,AI 根本不了解它。为了解决这个问题,这个 MCP 服务器为 LLM 提供了访问 Revit API 文档及其他相关内容的权限(见Rvt_Docs_Tbc_Embedder)。在底层,它同时使用 rvtdocs.com 和 revitapidocs.com,如果启用了,还会使用构建程序员博客。 只需问问你的MCP客户,Revit API文档对某件事说了什么,它就会用多种工具组合自己探索API文档。 - : 在 Revit API 文档中搜索类、方法和属性(或任何 API 实体)。- : 通过 URL 或实体名称检索 API 实体文档页面的内容。- : 对 The Building Coder 博客嵌入的向量空间进行语义搜索。 - : 获取用于Revit API的代码示例并使其可访问。

概述(AI 翻译)

概述

由于Revit API的表面积极其庞大,AI经常产生幻觉 类、方法、属性,甚至整个命名空间。此外,有用的, 但非官方或不常见的API用途如此小众,AI根本没有 对它的知识。为了防止这种情况,这个MCP服务器为LLM提供了Revit API的访问权限 文档及其他相关内容(参见 Rvt_Docs_Tbc_Embedder)。下 罩头,它同时使用 rvtdocs.com 和 revitapidocs.com,如果启用了,则 Building Coder 博客。

只需问问你的MCP客户Revit API文档对某些内容说了什么,它 将结合多种工具单独探索API文档。

特色

  • Search Revit API:搜索类、方法和属性(或任何 API) entity)在Revit API文档中。
  • 访问文档:检索API实体文档页面的内容 无论是通过网址还是实体名称。
  • 搜索/访问TBC博客:在向量空间上执行语义搜索 构建Coder博客嵌入。

功能(计划中)

  • 代码示例:获取用于Revit API的代码示例并制作 易于接近。看 RevitSdk样本。或者也许

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

Revit API MCP Server

Overview

Because of the absurd surface area of the Revit API, AI often hallucinates classes, methods, properties, or even entire namespaces. Furthermore, useful, but unofficial or uncommon uses of the API are so niche that AI’s have no knowledge of it. To curb this, this MCP server provides LLMs access to Revit API documentation and other related content (see Rvt_Docs_Tbc_Embedder). Under the hood, it uses both rvtdocs.com and revitapidocs.com, and if enabled, the Building Coder Blog.

Simply ask your MCP client what the Revit API docs say about something and it will use a combination of tools to explore the API docs on its own.

Features

  • Search Revit API: Search for classes, methods, and properties (or any API entity) in the Revit API documentation.
  • Access Documentation: Retrieve the content of an API entity’s docs page either via the url or the entities name.
  • Search/Access TBC Blog: Perform semantic search over a vector space of The Building Coder blog embeddings.

Features (Planned)

  • Code Examples: Get code examples for Revit API usage and make them accessible. See RevitSdkSamples. Or maybe even entire repos, like those from ricuan-io, Nice3point, chuongmep, kilkellym, and of course jeremytammik.
  • More Resources: Add other content to the vector store. Candidates include tbc-related pdfs, random blog posts, and Autodesk University resources.
  • Caching (Unlikely): Cache responses to reduce traffic to the api doc sites.

Tools

This repository provides four MCP tools for working with Revit API documentation:

  • search-docs - Search Revit API documentation to find entities matching your query. Returns entity names, descriptions, namespaces, types, and URL slugs for further exploration (but not the documentation itself).

  • retrieve-doc - Retrieve a single Revit API documentation page using its URL slug. Use this after getting a URL slug from a search operation.

  • retrieve-docs - Get full documentation content for multiple Revit API entities based on a search query. Useful when you need complete documentation content, not just search results.

  • search-library - Search a comprehensive library of Revit API learning resources including blog posts, code examples, PDFs, and practical guides. Powered by OpenAI’s vector store for semantic search.

Setup

Download the executable for your OS from Releases. Or you can clone and build from source using deno task compile. Add this executable somewhere in your file system that makes sense. Good practice for Windows is /bin/, but it can be anywhere.

Run path\to\executable -h in your terminal to see the help menu. FYI: This executable is useless to run in the terminal besides for the help menu and for

在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "revit-api-docs (macos-arm64)": { "command": "path/to/Rvt_Docs_MCP-macos-arm64" }, "revit-api-docs (macos-x64)": { "command": "path/to/Rvt_Docs_MCP-macos-x64" }, "revit-api-docs (windows)": { "command": "path\\to\\Rvt_Docs_MCP-windows.exe" }, "revit-api-docs (with search-library enabled)": { "command": "path\\to\\Rvt_Docs_MCP-windows.exe", "args": ["-v", "vs_xxx", "-k", "sk-proj-xxx"] } } }