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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.