"Interacting with a webpage using a browser plugin and live browser instance" matching MCP servers:

An HTTP MCP server for exploring CSV files that masks PII before any code execution, enabling safe data analysis with local or cloud LLMs.

A local, fully vectorized computational engine for stock market analysis that enables AI to perform factor calculation, strategy backtesting, IC analysis, and GPU-based multi-dimensional visualization using local DuckDB data.

Read-only MCP server for complete, reconciled reporting from live Zendesk data, designed for Cursor and other MCP clients.

Launches/connects to the visible draw.io desktop editor and edits its active graph model in real time, allowing AI agents to draw scientific figures step by step.

An MCP server that generates and manages nifdi diagrams as SVG files, bundled with skills that teach models in depth, placement grammar, and build workflow through natural language.

Enables transforming grounded AI answers into interactive information views such as comparisons, plans, checklists, timelines, and decision views, while preserving a plain-language fallback.

Enables MCP clients to watch and drive a running ResInsight, query reservoir simulation models, and render pictures and plots without touching the GUI.

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.

MCP server for managing a task graph with live visualization. Enables Claude Code to create, update, and link nodes (tasks, subtasks, ideas, etc.) while a browser viewer displays the graph in real time.

Enables agents to render shadcn-styled dashboards, forms, charts, and comparisons in a local browser via MCP tools.

Enables natural-language queries about sales metrics, returning interactive charts inline in chat via MCP Apps with a markdown fallback for unsupported hosts.

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 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.

Calculates Taiyi Shenshu (太乙神數) based on a given datetime and returns structured text and a board PNG image.

Zero-dependency charts for Python and AI agents. SVG and PNG, 15 chart types, a one-line MCP server, and a Claude skill.

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).

A Model Context Protocol server that gives an LLM a structured visual layer to describe what exists and get back a clean, precise SVG diagram instead of ASCII art.

Enables natural language querying of brain volumes (NIfTI) with a fixed set of tools, returning visualizations and reproducible nilearn code.

A unified Model Context Protocol server for data engineering and analytics that lets LLM clients query, profile, transform, and visualize data using DuckDB and PySpark, while keeping raw data out of the model's context through read-only, bounded, and audited operations.