"The most widely used models" matching MCP servers:

An MCP server that gives models semantic context about a data warehouse, including table meaning, units, lineage, and health, to reduce guessing.

Bridges Microsoft Foundry agents and Power BI semantic models into GitHub Copilot Chat, enabling users to query and modify measures as the signed-in user via MCP.

Connect Claude to your Power BI semantic models. Browse workspaces, tables, and measures, run DAX queries, and get results — with large datasets automatically saved to local CSV files to protect the LLM context window. Includes a query history log for cross-session reuse and auditability.

This server acts as a MCP bridge to interact with the Cribl REST API. It allows AI models or other MCP clients to query and manage Cribl configurations.

Enables discovery of Power BI workspaces and semantic models via REST API and Microsoft Modeling MCP, with authentication options including service principal and device login.

The Excel to JSON MCP provides a standardized interface for converting Excel and CSV data into JSON format using the Model Context Protocol.

Enables AI agents to discover and query data federated across MySQL/MariaDB, PostgreSQL, ClickHouse, S3 and Kafka with SQL, exposing tools to list databases, schemas, tables and connections, describe columns, search objects, inspect table statistics, run EXPLAIN, and execute arbitrary statements. It runs locally over stdio against a PostgreSQL-wire endpoint and returns structured results or SQLSTATE-coded errors.

Enables language models to model SAP BW/4HANA through the BW Modeling Tools REST interface, with intent-based tools for searching, reading, writing, activating, querying data, monitoring, runtime actions, and transports. It uses compact schemas and safe-by-default permissions to complete changes in few calls.

An open-source MCP server that connects to various data sources (SQL databases, CSV, Parquet files), allowing AI models to execute SQL queries and generate data visualizations for analytics and business intelligence.

The JSON to Excel MCP provides a standardized interface for converting (1)JSON data (2)URL pointing to JSON files into CSV format

Enables large language models and AI agents to securely and efficiently interact with Apache Kafka clusters through the Model Context Protocol.

An MCP server that allows AI models to create data visualizations using Vega-Lite syntax by providing tools to save data tables and generate visualizations from them.

Enables MCP clients to inspect, validate, transform, and query CityJSON models, with support for conversion, persistence, and 3D geometry validation.

This MCP server enables interaction with the Polytomic API to manage data connections, models, and synchronization tasks. It supports both Reverse ETL and ELT operations, allowing users to trigger syncs, monitor execution status, and configure data pipelines.

A tool for SHACL-based assessment, comparison, and coverage analysis of digital passport data models, designed for AI-agent orchestration.

Exposes safe JSON contracts for validating and preparing datasets, running supervised fine-tuning, preference learning, RL, distillation, and evaluation, and managing checkpoints and exports through the Tinker SDK and Cookbook. It lets agents discover models and Hugging Face datasets, plan and execute training recipes, compare experiments, and export selected models.

An MCP server that exposes VeloDB analytics data to AI clients through a governed semantic metrics layer (MetricFlow) and raw SQL fallback, with multi-workspace isolation, staging workflows, and a web UI for managing models.

Enables AI agents to query Chinese A-share market data — real-time quotes, K-lines, order books, financials, fund flows, dragon-tiger lists, sectors, convertible bonds, macro data, and factor screening — through 24 tools, five of which require no API key. It can be used via a hosted endpoint with no installation or self-hosted locally over stdio.

Enables Claude, Cursor, or any MCP-compatible client to query Apache Kafka topics, consumer groups, schemas, and cluster health in natural language, served from your own self-hosted instance. Access is read-only and inherits the token holder's existing RBAC, so only metadata reaches the model unless a capped message-reading tool is explicitly used.

Enables DeepSeek Harness models to directly call local ArcGIS Pro via MCP tools for reading projects, layers, GDB structures, and executing Buffer/Clip/custom ArcPy operations locally.

A production-ready MCP server that provides comprehensive dbt project quality assessment for any GitHub repository, enabling AI agents to analyze dbt models, check metadata coverage, and map data lineage.

MCP server for the OrionBelt Semantic Layer. Enables LLMs to explore governed semantic models, compile YAML metric definitions into optimized SQL across 8 engines (BigQuery, ClickHouse, Databricks, Dremio, DuckDB, MySQL, PostgreSQL, Snowflake), and execute analytics queries via natural language. Works with Claude, Cursor, Windsurf, and Copilot.

Enables querying open Power BI Desktop models locally, including discovering instances, listing tables and measures, and running DAX queries without cloud login or publishing.

Provides read-only access to MetaTrader 5 market data, trading history, and technical analysis through Python execution. Supports querying price data, calculating indicators, creating charts, and generating forecasts with Prophet and ML models.

Enables agents to inspect dbt model semantics, retrieve contracts and lineage, and verify that edits do not change what models mean.

Enables read-only access to Board models through an authenticated Firefox session, listing models, entities, and cubes with their metadata without exposing data editing or API credentials.

MCP server for connecting to Microsoft Fabric and Power BI semantic models, enabling workspace browsing, dataset management, TMSL retrieval, DAX queries, model creation/editing, and includes a Best Practice Analyzer with 71 rules.

Enables language models to run data-quality checks and profiling on local files, using dbt-style assertions like not_null, unique, relationships, and accepted_values.

Remote and centralized MCP server that enables AI models to interact with Microsoft Fabric (workspaces and items) via the Fabric Core REST API, using delegated OAuth 2.1 authentication with Microsoft Entra ID so each user's permissions and restrictions are respected.

Turns Google Sheets, CSV, Excel, and Parquet files into durable, queryable data for AI agents. Lets clients securely discover datasets, inspect semantic models, run bounded analytics, and manage approved semantic overlays.