"Optimizing AI Model Thinking, Token Usage, and Context Size" matching MCP servers:

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.

An unofficial MCP server for generating infographics and visuals from text using the Napkin AI API, enabling AI assistants to create professional diagrams, mindmaps, and charts.

MCP server for AI-driven CAD operations, enabling parametric modeling, build, inspection, measurement, rendering, and diff comparison with STEP, DXF, and GLB export.

Enables AI-native statistical analysis and reproducible research workflows through MCP, including natural language planning, protocol-based analysis, Python/R cross-validation, and publication-ready figure generation.

An MCP server for generating offline charts using Apache ECharts SVG SSR and rsvg-convert, optimized for Kylin ARM64 with 64KB page size.

MCP server for A-share stock technical analysis and AI prediction, enabling LLM-based interaction to analyze stocks.

Enables controlling Power BI with AI through natural language commands for creating DAX measures, explaining metrics, suggesting KPIs, and organizing models.

MCP server for AI Diagram Maker — generate software engineering diagrams from natural language, code, ASCII diagram, images, or Mermaid. Inline diagram rendering using MCP apps UI and diagram URL in responses. Works with Cursor, Claude Desktop, Claude Code, and any MCP-compatible AI.

Enables AI hosts to generate and open Mermaid diagram links in Markdown files, providing tools for syncing, listing, and injecting diagrams via the Mermaid.ai editor.

Enables AI clients to generate over 26 chart types via MCP, automatically starting a private rendering service.

Enables users to create, validate, view, and export system stock-and-flow maps from a versioned JSON model through MCP-capable hosts over local stdio or hosted Streamable HTTP. Supports causal-loop and nested-level mapping while keeping submitted model content with the caller and requiring no LLM provider key.

Enables AI agents to produce brand-compliant dashboards by emitting validated JSON specs instead of raw HTML/CSS, which the server renders automatically while cutting token usage.

Enables Codex to control a Gephi 3D network view through natural language, including network generation, 3D layout, node focus and neighbor highlighting, layered views, and PNG/PDF export.

Enables creating surveys, validating questions, collecting responses, and generating analysis reports.

Enables conversational spatial SQL queries in plain English, turning natural language questions into validated PostGIS operations and rendering results as GeoJSON on an interactive map.

MCP server that provides F1 telemetry analysis, tyre degradation modeling, and pit strategy recommendations, delivering race engineer-style calls grounded in real data. It exposes tools for degradation fits, fuel correction, and strategy reasoning via LangGraph.

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.

AI-powered data visualization MCP server that generates publication-ready charts from natural language descriptions while keeping data local.

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.

Enables asking natural-language questions about WHOOP recovery, sleep, HRV, strain, and workouts inside Claude, Codex, and GitHub Copilot. Provides read-only tools, resources, and prompts for personal health analytics, along with HYROX and triathlon tracking and a local chart-first dashboard.

Opens, inspects, and renders DXF/CAD drawings for AI agents: describe_dxf returns structured facts (layers with actual drawn colors, units, bounds, text content) and render_dxf returns PNG images. On MCP Apps hosts like ChatGPT and Claude, view_dxf opens an interactive in-chat viewer with pan, zoom, and layer toggles.

Converts plain-English stock requests (e.g. "compare Apple and Microsoft YTD") into validated yfinance/matplotlib scripts, AST-checked and executed in a sandbox to produce chart PNGs. Exposes parsing, saving, execution, and history-listing tools to Claude Desktop and Claude Code through FastMCP, backed by local Ollama/DeepSeek-R1 or cloud Groq/GPT-4o models.

MCP server for rendering Object-Process Methodology (OPM) models from YAML to SVG diagrams and OPL sentences, with validation and generation capabilities.

MCP server and ChatGPT/Codex plugin for Persian-language gold market decision support, connecting to WallGold accounts via OAuth to provide live prices, portfolio valuation, multi-dimensional analysis, risk policy, and trade previews.

Automates sales data analysis by cleaning CSV, generating AI insights, creating interactive HTML dashboards, exporting PDF reports, and emailing them, all via MCP tools and multi-model AI fallback.

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.

Validates and renders declarative JSON diagram specs to themeable SVG. The format has no coordinates, so a model writes structure and the renderer does the layout; tools: validate, render, kinds.

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.

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.