"Understanding Inference Models" matching MCP servers:

Provides deterministic tools for understanding, transforming, and verifying structured data via MCP, enabling rule inference from examples and verification of transformed records.

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

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.

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.

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 incremental model scoring over an append-only event log, with a tamper-evident, hash-chained audit trail so every decision can be reviewed and independently re-verified.

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

Enables structured document understanding of local PDFs via a dual-extract MCP server, combining MinerU text/layout and Qwen3-VL vision with fusion adjudication for field extraction, tables, formulas, and validation. Fully local and offline.

Enables local and offline XLSX header cataloging, candidate relationship inference, and Oracle SELECT/WITH SQL generation without accessing databases or executing SQL.

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.

Connects MCP clients to databases like Snowflake, BigQuery, and Databricks through Alkemi's data platform, enabling natural language database queries with proper schema understanding and metadata management for consistent team-wide access.

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.