"All items" 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.

Enables Claude to pair with an Apple TV dashboard via a short code, compose and push custom information decks, and keep them refreshed through scheduled tasks, with checked-off items reported back so Claude can complete them at the source.

Enables Claude Desktop to view and interact with the currently open QGIS project, including layers, styling, selections, Processing algorithms, attribute editing, and geocoding, all running locally.

Enables coding assistants to replay a backtest's market orders against the trades that followed them, producing fills and slippage statistics, and to turn a bars CSV into a self-contained HTML tearsheet that splits returns into fees, funding and slippage. All work runs locally over stdio on files you supply, with no data sent anywhere.

Enables local, private analysis of CSV and TSV files through natural-language agents such as Grok Bot and Cursor, offering file listing, profiling, SQL-like queries, summaries, group-bys, pivot tables, cleaning previews and generated charts. All computation happens on the user's own machine against an allowlisted folder, with no network calls, telemetry or data leaving the host.

Enables interactive learning and visualization of Binary Search Trees and AVL Trees through operations like insertion, deletion, and tree traversal, with real-time balancing rotations.

Enables conversational input of HR, financial, and qualitative organizational data to run a hypothesis-based diagnostic that computes metrics, benchmarks cohorts, assesses growth stages and competing hypotheses, and recommends actions. All processing stays on the user's machine and outputs a structured JSON result plus an offline HTML dashboard.

A unified MCP server that lets Claude query any SQLite database and build live Streamlit dashboards — all from a single conversation.

Enables coding agents to turn finished sessions into Strava-style achievement cards with distance, elevation, effort, badges, and personal records, plus profile, activity feed, season recap, and leaderboard tools—all measured from session transcripts rather than self-reported.

Enables MCP clients to validate a JSON report definition and render it into a PDF, Excel, Word, HTML, or CSV file written to disk, returning the output path and size rather than the file's bytes. Errors are reported as fixable problems naming the exact path at fault, and all host-level limits stay under the launching host's control.

Enables ChatGPT's desktop Codex app to query a live 1C (1С) database through OData in read-only mode, so users can ask plain-language questions about sales, stock, items, and counterparties, and get answers, charts, and dashboards without exports or programming.

A display-layer MCP server that renders text-game state — stats, inventory, locations, characters, dice results, and choices — as stable, themed cards in ChatGPT or Claude chats. It offers five visual skins and clickable option buttons that send the chosen action as the user's message, while leaving all rules and narrative to the AI.

Enables clients to create, query and edit QGIS projects and vector data in an isolated, new headless PyQGIS process, exporting GeoJSON/GeoPackage, saving and reopening editable QGZ bundles, and rendering PNG maps through typed MCP tools. All operations are workspace-relative with strict path and geometry validation, and never attach to or modify a running QGIS desktop session.

A lightweight MCP server that provides real-time Mermaid diagram syntax validation with support for all diagram types.

Metabase includes a built-in Model Context Protocol (MCP) server that lets AI clients connect directly to a Metabase instance. It uses the Streamable HTTP transport and builds on Metabase's Agent API to expose tools for searching, exploring, querying, and visualizing data — all scoped to the connecting user's permissions.

OrionBelt Analytics is an MCP server that analyzes relational database schemas and generates RDF/OWL ontologies with embedded SQL mappings. It provides relationship-aware Text-to-SQL with automatic fan-trap prevention, GraphRAG for intelligent schema discovery, and interactive charting -- all accessible through any MCP-compatible AI client.

A statistical analysis MCP server offering 30 tools for descriptive statistics, hypothesis tests, regression, and time series, all returning Markdown reports with automatic interpretations to enable AI agents to perform comprehensive data analysis.

Enables AI agents to run a full QFD session over the Model Context Protocol: build and edit a House of Quality (stakeholder needs, measurable characteristics, relationship cells, trade-off roof, work items), validate it, and read back priorities, gates, the diagonal build order and item progress. It also exports the house as TSV, CSV, JSON, SVG or an Excel workbook, with optional file persistence so a person can keep editing where the agent left off.

Enables AI agents to inspect geospatial vector and raster metadata and run bounded analysis on administrator-registered datasets, including planar buffering, clipping, spatial joins, and PNG map rendering delivered as checksummed artifacts. All data access is read-only and controlled through a curated dataset catalog.

Enables AI agents to drive a persistent, isolated ParaView session for scientific visualization: creating and editing spheres, clipping with planes, importing single-file VTI/VTP/VTU datasets, extracting contours, exporting verified datasets, saving native PVSM states, and rendering display-backed PNG previews. All operations are confined to a single operator-owned workspace on a Linux-only, display-backed host, with no attachment to existing GUI pipelines.

Turns an AI client into a slide author that produces single self-contained HTML decks with live diagrams, step-by-step reveals, in-place text editing and PDF export. It also lets the AI verify its own work through layout audits and screenshots, all locally with no API key.

Enables building configurable workplace dashboards with eight MCP apps/widgets for agenda, brief, attention, goals, leave, learning, updates, and actions, all backed by synthetic live data via a standard MCP server.

Exposes a live PyMca GUI session over MCP so an agent can plot curves, fit peaks and edges with statistical uncertainties, normalize, align and compare spectra, run PCA, linear-combination fitting and batch analyses, and generate reports. Every action runs on the objects of the open session, so agent commands and manual mouse work can be interleaved, with all steps recorded for replay and undo.

Enables AI assistants to pull live quotes, quarterly financials, technical indicators, FII/DII flows, option chains with IV, corporate filings, IPO data and portfolio P&L for all 8,200+ NSE and BSE listed stocks, plus a 326-ratio screener and index heatmaps. Connects either remotely over OAuth or locally via npx/uvx to Claude, ChatGPT, Cursor, VS Code, Codex and Gemini CLI.

Enables users to capture real MetaTrader 5 chart snapshots with custom indicators and fetch market data through natural language in Claude Desktop.

Enables users to request live currency conversions in plain language inside Claude or ChatGPT, displaying an interactive in-chat card where changing the amount instantly updates all shown currencies.

A Model Context Protocol (MCP) server that enables seamless integration between MATLAB and MCP-compatible applications like Claude Code. Execute MATLAB code, manage workspace variables, create plots, handle data I/O, and more - all through a token-efficient MCP interface.

Enables creating, managing, and publishing Datawrapper charts.

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.

Enables a local assistant to drive a full data workbench: ingest messy files, clean them with versioned and undoable steps, enforce quality rules, build charts and dashboards as code, train quick models, and ask questions of the data—all on the user's own machine.