PBIFORGE
PBIForge — Power BI .pbix generator MCP server generate .pbix files from dashboard image and prompts using a local hosted llm
README
ReportForge PBI
Local Claude Desktop MCP app for generating Power BI .pbit reports from CSV
datasets, natural-language instructions, and reference-image styling.
The recommended setup is local stdio MCP. Claude Desktop runs this project on
your machine, so the MCP can read local CSV files and save generated reports
back to generated_reports/.
Capabilities
- Create a Power BI dashboard from a local CSV path.
- Create a dashboard from pasted CSV text or base64 CSV.
- Profile CSV columns and infer KPIs, dimensions, measures, date fields, and slicers.
- Generate a Power BI semantic model, Power Query M, report layout, theme, and
.pbit. - Apply template-based layouts inspired by the reference dashboard images: KPI rail/grid, central chart panels, right filter panel, light canvas, white cards, subtle borders, and capped visual counts to avoid clutter.
- Export a local
.pbitfile for Power BI Desktop. - Optional Anthropic-powered features for natural-language report creation, visual edits, styling edits, and image theme extraction.
Quick Start
Download ZIP option:
- Download
reportforge-pbi-local.zip. - Extract it.
- Open PowerShell inside the extracted folder.
- Run:
.\setup_local.ps1
Git option:
git clone https://github.com/twilize5/reportforge.git
cd reportforge
.\setup_local.ps1
Then install pbi-tools.core and configure Claude Desktop using
LOCAL_SETUP.md.
Main Files
mcp_server.py- MCP tools exposed to Claude Desktop.mcp_stdio.py- stdio entrypoint for Claude Desktop.main.py- optional local FastAPI server.auto_intent.py- deterministic CSV profiling to dashboard generation.file_writer.py- writes Power BI project files and injects DataMashup/layout.prompts/- prompts for Anthropic-powered paths.setup_local.ps1- creates local venv and installs Python dependencies.run_mcp_stdio.ps1- starts the MCP stdio server.run_api.ps1- starts optional local HTTP API on port 8000.make_local_package.ps1- creates a clean distributable ZIP.
Docs
LOCAL_SETUP.md- local installation and Claude Desktop configuration.CLAUDE.md- project knowledge and capability notes.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。