"How to move the mouse and navigate the browser" matching MCP servers:

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

Options analytics an agent can drive: import a permitted chain, solve implied volatility, build a sixteen-Greek ladder, map dealer gamma walls, rank twenty-three structures, run a GARCH-t simulation with a convergence gate, and backtest with modelled premiums. Twelve stdio tools; every output is a schema-validated JSON file with source, assumptions and a degraded flag. Research only, no orders.

Embeds live, interactive Tableau dashboards in ChatGPT, pushing mark selections to the model so questions about specific data points are answered with live queried numbers.

Enables turning data into map images of countries, states, provinces, counties, continents, and the world, including choropleths, category maps, and pinned locations.

Enables rendering, validation, formatting, and inspection of D2 diagrams via the Model Context Protocol, using WASM for rendering without requiring the d2 binary.

Renders word-sized charts — sparklines, bars, bullets and 100+ more types — to self-contained SVG with generated alt text, small enough to sit inline in a model's reply or a table cell. Three tools: find the right chart for a question, get its wiring, and render it.

Enables querying Tableau lineage through the Metadata API via MCP, supporting impact analysis, where-used lookups, and content search. Provides read-only tools for answering natural-language questions about workbooks, datasources, fields, and dependencies.

A demo MCP server that returns an interactive dashboard (bar chart with dataset selector) as an MCP App via the official MCP Apps extension (SEP-1865).

An MCP server that lets Claude analyze your TradingView charts by reading the window and taking screenshots, with no write tools or trade execution.

Provides AI agents with read-only access to live chart context, candles, drawings, indicators, and provider status from the MyLinedChart desktop app, all running locally.

Enables LLMs to generate visual summary reports from CSV datasets using MCP Resources, Tools, and Prompts, without exposing raw data to the model.

A Model Context Protocol server that renders Apache ECharts options to SVG, enabling AI agents to generate deterministic charts server-side without a browser.

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.

Enables users to create, inspect, analyze, format, and chart Excel workbooks by having the client LLM write Python that runs in a fresh, network-restricted Docker container. Exposes a single execute_python tool with access to openpyxl, pandas, numpy, and matplotlib, persisting files between calls.

MCP server that enables natural-language-driven, headless HEC-RAS modeling, letting agents inspect, edit, run, compare, and plot 1D/2D hydraulic models without the GUI.

Enables LLMs to safely execute pandas code for data analysis and generate interactive visualizations through the Model Context Protocol.

Wraps a climate data-processing pipeline so agents can inspect the config schema and available sample CSVs, validate an inline JSON config, and run the pipeline to return a monthly summary table plus a rendered plot, with file access sandboxed to the data and outputs directories.

Turns a CSV — or a public dataset named in plain English — into an animated chart video. Every numeric claim in the generated narration is recomputed from the source rows before export, and a claim that does not reconcile blocks the export rather than shipping.

Provides live weather radar and text-based radar maps for any location via the get_weather tool, returning structured data and character grid visualizations readable by both humans and LLM agents.