Power BI Report MCP Server
Related Servers
Alternatives to Power BI Report MCP Server
No user-submitted related servers found.
Related Servers
- AlicenseBqualityCmaintenanceEnables MCP-compatible AI clients to build and modify Power BI reports through natural language, including pages, visuals, themes, filters, and formatting using local PBIR files without REST API keys or the Power BI service.57MIT
- AlicenseBqualityAmaintenanceEnables AI agents to author and edit Power BI files locally (.pbix/PBIP), covering semantic models, reports, and Power Query M with 490 tools.10023 npm3Cryptographic Autonomy 1.0 (Combined Work Exception)
- AlicenseAqualityBmaintenanceEnables local Power BI project (.pbip) automation, including model (TMDL) and report (PBIR) layer manipulation, without cloud dependencies. Provides 56 tools for building, editing, and validating reports and measures through natural language prompts.13MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI assistants to read and modify Power BI Desktop files programmatically, including querying models, creating measures, and managing relationships through natural language.256-
- AlicenseNot gradedqualityCmaintenanceEnables an AI assistant to build Power BI projects end to end: data modeling (tables, DAX measures, relationships, calculation groups, roles, field parameters) against an open Power BI Desktop via TOM/XMLA, and reports (pages, visuals, formatting, bookmarks, themes) as PBIR files in a .pbip project. Every visual is cross-checked against the real model before being written, so generated dashboards don't break on open.MIT
- AlicenseBqualityDmaintenanceBuild Power BI reports with natural language through an MCP server that connects AI assistants to Power BI's PBIR file format for creating pages, visuals, themes, and filters locally.25721MIT
TDQS
Scored across 58 tools
Despite 58 tools, most target clearly distinct resources and actions, and the descriptions actively disambiguate the risky pairs (auto_layout vs layout_grid, clear_filters vs remove_filter, apply_theme vs set_report_theme, format_visual vs set_visual_title). A few real overlaps remain — set_visual_title vs format_visual title routing, and set_datapoint_colors vs set_conditional_format vs format_visual — but descriptions steer correctly in most cases.
The surface is uniformly snake_case with a pbir_ namespace prefix, which makes the family instantly recognizable. A handful of names break the verb_noun pattern (pbir_model_usage, pbir_guide, pbir_auto_layout, pbir_layout_grid) and the bulk_* variants live after the prefix, but overall it reads consistently.
58 tools is far beyond a comfortable single-server surface, even for a complex PBIR editing domain; page, visual, filter, theme, bookmark, layout, and bulk operations each sprawl across many entries. The on-demand pbir_load_tools mechanism is a sensible mitigation, but the advertised count is still heavy enough to strain tool selection.
Coverage is genuinely deep: full page/visual lifecycle, filters, themes with diff/audit/list, bookmarks, formatting, bulk ops, layout validation, and semantic-model cross-referencing. Minor gaps exist — bookmark state capture is deferred to Desktop, and data/measure authoring is delegated to a separate modeling MCP — but agents can work around both.