"How to Connect to MongoDB" matching MCP servers:

Enables discovery of Fabric/Power BI workspaces and semantic models, execution of DAX queries, and generation of executive HTML reports with visualizations.

Enables an agent to turn a paper's draft into editable Figma frames for publication-ready figures, checking every number against the paper and verifying the exported PDF.

Enables agents to turn structured data into production-ready static maps, returning rendered PNG and SVG URLs along with an editable map link.

MCP server that lets agents create and update persistent concept maps via the NodeLand API, returning shareable URLs for humans to view, embed, and keep editing.

Geneva MCP brings production-grade forecasting directly into AI assistants and coding agents. Connect any MCP-compatible client to the Geneva Forecasting Engine and run rigorous time series forecasts through natural conversation.

Turns plain text or Markdown, web pages, and local PDFs into editable Markdown outlines that can be rendered as standalone, offline-capable interactive HTML mind maps. Works with any MCP client with no API key required, since the connected model writes the final outline from a draft and cleaned source text.

Enables AI agents to push numbers and metrics to iPhone Home Screen, Lock Screen, and Live Activities widgets and read them back.

Enables AI assistants to compile distribution feeders, run power flow, voltage and thermal violation checks, short-circuit and Thévenin impedance studies, hosting capacity and QSTS analyses, and add or edit elements, through 20 typed tools that return structured JSON or Markdown with the inputs that produced the results.

Enables AI assistants to connect to YNAB budgets, providing tools for accounts, transactions, categories, payees, and analytics, including search, bulk operations, and delta sync.

Enables agents to build and manage family trees, derive how people are related, and export diagrams or GEDCOM/HTML files through structured tools.

Connect QGIS to Claude AI through the Model Context Protocol (MCP), enabling Claude to directly control QGIS — manage layers, edit features, run processing algorithms, render maps, and more.

Lets an MCP client read PX4 SITL .ulg logs and answer why a flight failed or underperformed — failsafes, arming reasons, estimator validity versus simulator ground truth, and how late PX4 followed offboard velocity setpoints. It also lists, searches, scans and plots topics, messages and parameters across logs, replacing hand-written pyulog scripts.

QGISMCP connects QGIS to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control QGIS for project creation, layer loading, code execution, and more.

MCP server for introspecting PostgreSQL databases, providing tools to list tables, describe schemas, foreign keys, and generate DOT ER diagrams.

Enables sellers to connect their MercadoLibre Colombia account to Claude and manage their store in natural language, including sales dashboards, buyer-question responses, listing audits, product image/video generation, and competitor monitoring.

Enables users to connect their chat client to calculation tools for subsurface geological models, perform model checks and scenarios on exported Petrel/RMS data, and inspect reports and 3D scenes through a local viewer.

Enables ChatGPT and Claude conversations to display accessible interactive charts and lets models navigate readers through data points using speech, braille, and sound.

Enables AI assistants to connect to an industrial BI platform and read or build manufacturing dashboards, OEE reports, schedules, spreadsheets, forms, calendar events, and 3D CAD parts through natural-language tools.

Enables Claude Code and other processes to control the lys interactive multi-dimensional data analysis and visualization platform by executing Python commands in it and viewing the resulting lys and matplotlib graphs. It connects over a local socket or TCP to a lys instance running in remote mode.

Enables MCP-compatible agents to render privacy-first, deterministic Chart.js charts locally as PNG, SVG, PDF, or JSON, with configurable Sotheby's-inspired editorial themes per session.

Enables MCP clients holding a control key to create, update, publish, and unpublish dashboards and their charts, plus read-only access to dashboards, view stats, and audit logs. Published dashboards are viewable through public links in a minimal web UI, where viewers can request tweaks that the agent applies via these tools.

Enables AI assistants to generate and render individual and composite Human Design charts, explore authorized chart and library data, and manage account usage and Website Builder projects with secure OAuth and entitlement filtering.

An MCP server that enables Claude Code/Codex to directly control PsychoPy for designing, running, and analyzing psychology experiments with literature-calibrated paradigms.

Enables agent sessions to drive OriginPro via COM for plotting XY data, performing linear fits with R2, and exporting PNG images.

Enables interactive kepler.gl maps to render inside MCP host chats and lets agents control them through map tools such as loading data, adding layers, and switching basemaps.

A TypeScript/Node.js MCP server that wraps the Metabase REST API, enabling AI agents to execute queries, explore schemas, and build dashboards through structured tool calls.

Enables AI assistants to access and manage Metabase analytics through 96 tools for dashboards, cards, databases, tables, collections, and query execution.

Enables users to prepare and validate market data, launch and control backtests, and retrieve results, causal explanations, and self-contained reports through stdio tools. It also supports polling or canceling jobs and running sweep, walk-forward, factor, and study research workflows with bounded pagination and reproducible artifacts.

A standalone stdio MCP server that exposes 13 resources, 3 prompts and 7 tools for assembling interactive, replayable HTML interfaces such as calculators, charts, maps, flowcharts and small apps. It returns the generated HTML document for the calling client to decide whether and how to display.

Enables local AI assistants to inspect Windows disk usage with treemap and folder X-ray views, retrieve cleanup previews, and receive application removal guidance, while exposing only non-destructive commands through MCP.