"Using Gemini for execution and Claude for problem-solving" matching MCP servers:

A safety-gated Python MCP server for Metabase that lets MCP clients and agents inspect Metabase, run governed queries, and create or maintain dashboards, cards/questions, collections, snippets, permissions, and other Metabase assets through the Metabase REST API.

Enables LLMs to interact with Kibana through composable toolboxes for building dashboards, managing data, and handling alerts, among other operations.

Provides aerodynamic analysis tools through MCP, enabling geometry generation, meshing, CFD solving, and visualization for 2D airfoils.

MCP server for Microsoft Power BI and Fabric, enabling Claude to discover workspaces, semantic models, generate and execute DAX queries, and retrieve report metadata via device-code authentication.

A production-grade MCP server that provides tools to fetch historical stock data, company information, and technical indicators (SMA, EMA, RSI, MACD, Bollinger Bands) via yfinance, and includes a Flask web dashboard for visual analysis.

MCP server for generating diagrams, charts, and visualizations using Gemini image generation on Vertex AI. Supports auto-detection of diagram types, multiple style modes, and iterative refinement.

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

Enables your own ChatGPT to build and manage a collaborative work board—dashboards, categories, datasets, monitors, and policies—through typed WebMCP tools, with human approval, audit trails, and guardrails enforced on every action.

A minimal, dependency-free MCP server that renders interactive widgets (like bar charts) inline in Claude, ChatGPT, and Grok from a custom connector.

Enables rendering interactive UI widgets and data visualizations for Claude.ai through MCP, supporting callback-based forms and client-side charts.

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 AI assistants to drive a live TradingView chart in Chrome, turning natural-language trading ideas into compiled Pine Script indicators, adding them to charts, and reading back results. It also supports chart navigation, indicator management, screenshots, and strategy tester backtest results.

MCP server providing data analytics tools for AI agents to load, clean, analyze data, generate charts and dashboards.

Enables AI assistants to control a logged-in TradingView chart in Chrome, including writing and compiling Pine Script indicators, adding them to charts, changing symbols and timeframes, capturing screenshots, and retrieving strategy tester results.

Enables AI assistants to query Power BI datasets via MCP, automatically anonymizing sensitive data before it reaches the AI, and generating rich HTML reports from natural language questions.

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.

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

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

MCP server that lets agents create, display, and export rich UI widgets (cards, dashboards, charts, forms) inline in conversations, with interactive iframe support in MCP Apps hosts and PNG image fallback for other clients.

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.