"How to conduct web searches" matching MCP servers:

Official draw.io MCP server: create diagrams from Mermaid, XML or CSV, shown inline in Claude, ChatGPT, VS Code and Cursor or opened in the draw.io editor. Searches 10,000+ shapes.

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.

Generates pure CSS and SVG charts for web pages and markdown docs, eliminating the need for chart libraries, and provides injection guidance.

Enables AI clients to query live Minecraft recipe data and compute recipe trees, production plans, and searches from a running game or disk snapshots, with markdown, TSV, JSON, and HTML outputs.

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

Enables creating executive presentation suites from a single prompt, generating PowerPoint, interactive web deck, KPI dashboard, whiteboard infographic, and vector PDF files through MCP.

Enables an AI assistant to load, query and edit a YAML or JSON graph file, with tools for adding, editing and removing nodes and edges, managing reusable styles and graph-level properties, and saving changes. Every change is written to the file immediately, so the same graph can be viewed and edited live in the companion web app.

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.

MCP server that tracks and searches Microsoft Graph API schema changes, permissions, and roles, with historical data and an interactive schema visualizer.

QuestDB MCP server connects coding agents to a running QuestDB Web Console. The agent gets tools to create notebook cells, run queries, and build charts.

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

A local stdio MCP server for a self-hosted GeoGebra 5.0 Web bundle. It enables executing GeoGebra commands with structured feedback, querying commands, evaluating CAS, managing state, and exporting images using headless Chromium.

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.

Provides data science, plotting, statistics, system, and web tools via MCP, with interactive CLI clients for OpenAI-compatible and Anthropic providers.

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.

Enables MCP-compatible hosts to perform live web research, process local transcripts or text into headlines and keywords, and generate 3D office visualizations from processed data.

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.

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 LLM clients or shell users to read and control a live TradingView Desktop chart, including chart state, OHLCV and indicator values, Pine Script editing/compiling, drawings, alerts, bar replay, and screenshots via the Chrome DevTools Protocol.

Enables AI assistants to fully manage the analytics platform through comprehensive tools for dashboards, cards, databases, and tables.

Enables connecting to any SQL database, exploring schemas, running queries, and visualizing results with interactive charts from Claude Desktop.

MCP server for rendering Mermaid diagrams and generating source-code diagrams, with tools to render text/files and produce dependency/class diagrams.

MCP server for managing Google Sheets via 23 tools, enabling read/write, formatting, sheet management, and data operations through natural language.

Enables AI agents to read and manipulate networks, tables, visual styles, and more in a live Cytoscape Web session through natural language, by connecting over Chrome DevTools Protocol.

Enables AI assistants to build and revise visual goal plans, compare competing routes, model possible futures and forecasts, track progress, and re-plan as circumstances change through MCP tools.