"Local AI Agent Toolkit" matching MCP servers:

Enables verifiable business intelligence over federated data sources, supporting semantic queries, drill-down to source rows, and raw SQL with explicit verification status.

A read-only MCP server that reports BI pipeline readiness, blockers, and the next allowed action for governed Power BI workflows. It never writes files, executes warehouse work, or grants human approvals.

MCP server that diagnoses Apache Spark job failures and optimizes performance using stack-trace analysis and LLM providers, supporting EMR and local sources.

Provides a stateful local Spark session for running PySpark and SQL cells, enabling local data exploration before deploying to Microsoft Fabric.

Agent-ready financial intelligence tools for AI agents. Two curated tools — get_stock_snapshot and get_company_metrics — that combine multiple data sources, derive signals (UNDERVALUED, STRONG, ACCELERATING), and pre-compute the math. One call, one agent-friendly response.

Local MCP server for AI Model Manager that captures SQL data-model metadata and exposes it to MCP clients over stdio.

50 tools and 400 functions for working with Excel/.xlsx spreadsheets — read/write, recalculate formulas, diff, repair broken references, and audit. Built for AI agents.

Enables AI agents to perform professional-grade geoprocessing tasks such as buffers, overlays, reprojections, and terrain analysis with deterministic tools and verifiable provenance.

Enables AI agents to discover and query enterprise knowledge documents and business metrics through standardized MCP tools, supporting retrieval, structured sales/order analysis, anomaly scanning, and data lineage lookups.

Enables local, read-only product-data checks for reviewing product records, comparing feed snapshots, and comparing dimensions against source rules, returning match or hold decisions without fetching references or modifying feeds.

The geospatial toolkit for AI agents. 6 tools, zero config — give any LLM the ability to parse, convert, query, and aggregate spatial data out of the box. Or just make a bounding box :) Every response includes a verification link to vibhorsingh.com/boundingbox so you can visually confirm results on an interactive map.

Enables AI coding agents to import xlsx config tables, audit growth curves, run battle and gacha simulations, and reverse-engineer game spreadsheet formulas through 17 read-only tools backed by deterministic, zero-dependency pure-function engines.

A tutorial implementation MCP server that enables analysis of CSV and Parquet files. Allows users to summarize data and query file information through natural language interactions.

Enables AI assistants to interact with Databar.ai's data enrichment API, allowing discovery, configuration, and execution of data enrichments across hundreds of providers using natural language.

Vizro is a low-code toolkit for building high-quality data visualization apps.

It gives Claude Code, Cursor, and Codex structured workflows and an MCP server for building data pipelines with dlt - covering REST API ingestion, transformations, data quality, and exploration.

Enables LLMs to interact with Google Analytics Admin and Data APIs to retrieve account summaries, property details, and custom metrics. It allows users to run core and real-time reports to analyze website performance and configuration via natural language.

Minimalistic MCP server that lets AI assistants inspect, quality-check, and clean CSV datasets through tools, resources, and prompts, without needing local file access.

An MCP server that exposes Estuary Flow pipeline operations as typed tools, enabling agents to inspect pipeline health, publish captures and materializations, edit/restart tasks, and read landed documents via tool calls.

Provides MCP tools for AI assistants to retrieve compact daily futures data packets, submit manual market data, run whitelisted crawlers, search research summaries, and save/read historical reports on demand for caustic soda, PVC, and coking coal futures.