"Accessing Hevy workout tracking app data" matching MCP servers:

An orchestrator MCP server that takes a plain-language app description and guides agents through a full workflow from intake to deployment, including design, audit, and maintenance.

Exposes a support-desk application through MCP tools and resources with populate/snapshot/restore hooks for reproducible RL training episodes.

A local stdio MCP server that lets any MCP client start a Codex thread and continue it by opaque thread ID through the codex and codex-reply tools, with fail-closed sandboxing and approval policies. It restores the removed Codex CLI MCP integration by bridging clients like OpenCode to the official Codex SDK.

Provides a deployable remote MCP server that serves interactive HTML widgets alongside tool results, enabling agent plugins for Cursor, Codex, and Claude Code.

Enables a supervisor agent to create, coordinate, steer, inspect, and interrupt multiple Codex agents as a subagent pool within an MCP host, running them alongside the host's own subagents.

Enables developers to host a minimal MCP endpoint that exposes a read-only Hello World tool and HTML UI resource for testing ChatGPT inline widgets, conversation side panels, and global sidebar apps.

A secure server that enables AI agents to access 2FA codes and passwords from the Authenticator App, allowing them to assist with automated login processes while maintaining security.

Production-oriented MCP gateway for managing Codex through a persistent codex app-server process, supporting threads, autonomous goals, approvals, and HTTP/stdio transports.

Enables a single MCP connector to route requests to independent local Chat and Codex runtimes, supporting workspace operations, process control, reviews, browser-backed tasks, and Codex workflows through one public ingress.

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Google Data Catalog (beta): https://www.cdata.com/download/download.aspx?sku=HGZK-V&type=beta

Exposes cQnce human-in-the-loop authorization as MCP tools, letting AI agents request and await human approval for risky actions. Includes request submission, monitoring, and project/team management capabilities.

Universal AI Agent OS — governed skills, rules, and commands for AI coding assistants (Claude Code, Augment, Cursor, Copilot, Windsurf). Read-only MCP bridge serves prompts and resources from a release-pinned content bundle.

Shape-shifting MCP hub — shapeshift() into 10,000+ servers at runtime. One entry point, no restarts, 7 registries.

Local Model Context Protocol (MCP) stdio server built with the official TypeScript SDK for discovering coding agents, requesting work, messaging, and tracking handoffs through a local Scout broker. Requires Bun 1.3+ and scout setup; the root README now documents MCP client configuration, tools, and direct implementation/test links (PR #28), for high-trust local developer pilots.

Enables any MCP client to answer with the live web by relaying requests over stdio to a Mac app that opens real pages and composes live parts into a Workspace. Automatically launches the companion app if it isn't already running.

MCP server that gives AI full control of a live Chrome browser via CDP, with 145 tools for framework-aware intelligence, evidence analysis, and SEO auditing. Connects to your existing Chrome via an extension, enabling interaction with dynamic and authenticated web pages.

Enables Grok Bot to connect to a local OpenScout broker through a hosted MCP gateway, allowing delegation of work, message exchange, and result tracking in one chat.

Proxies every Playwright MCP browser tool while automatically capturing what an agent learns on each site — fast paths, fixes, dead ends, and the site's observed internal API — and injecting it the next time any agent reaches that domain. Learned lessons and saved procedures become callable tools, so sessions start where previous ones stopped.

A unified Model Context Protocol server that aggregates multiple MCP servers into one, allowing AI assistants like Claude Desktop, Cursor, and Cherry Studio to connect to a single server instead of managing multiple instances.

A middleware API that connects AI assistants like ChatGPT to Captain Data tools for extracting information from LinkedIn company and profile pages.

Enables ChatGPT to discover and communicate with AI agents hosted on official websites via discovery metadata and conversational endpoints.

A Model Context Protocol server that provides financial tools for retrieving real-time stock data, analyst recommendations, financial statements, and web search capabilities for a LangGraph-powered ReAct agent.

An integration that enables AI assistants to interact with network data through a standardized protocol, providing AI-ready tools and interfaces for network automation and management.

Enables deployment of a customizable MCP server on Cloudflare Workers without authentication. Allows users to define custom tools and connect to clients like Claude Desktop or Cloudflare AI Playground for remote tool execution.

MCP server that connects AI assistants to Leapd, enabling them to launch and manage an AI-run business by creating tasks, deploying sites, and accessing business documents.

Enables real-time tracking of AI task starts and completions with integrated webhook notifications for monitoring activity. It allows users to log progress and send task-related event data to external services via configurable webhook URLs.

An MCP server for the pex.bot AI simulated crypto exchange that enables users to manage accounts, check real-time market data, and execute trades. It provides tools for profile management, order execution, and asset tracking within a simulated cryptocurrency trading environment.

Enables AI agents, including Claude, to interact with the AETERNA persistent world, leaving traces, sharing knowledge, and accessing world state and token economy.

Bridge to the MCP server built into SoftGlaze Browser, a multi-profile browser for Windows: AI apps can list, check and start isolated browser profiles (each with its own proxy and fingerprint), run macros and act inside pages. Changes wait for approval in the app; requires the SoftGlaze Browser desktop app.

Enables Claude Code to hand reviews, second opinions and tasks to the Codex and Antigravity desktop apps on one Windows PC and receive their answers back, without copy-pasting between apps. Each agent keeps working in its own app, with message threading, reply waiting, file reservations and delivery tracking over a local daemon.

Provides a centralized MCP-based system for managing and accessing multi-project memory banks remotely, with features like project isolation, file structure validation, and type-safe operations.

A server for task orchestration and coordination, facilitating task management with dependencies, multi-instance collaboration, and persistent task tracking.

Enables AI assistants to intelligently select and switch between different AI models (OpenAI, Anthropic, etc.) within the same conversation based on task requirements. Provides a unified interface for accessing multiple AI providers through a single MCP tool.

Enables AI assistants to interact with the Apify platform to manage actors, monitor runs, and retrieve scraped data from datasets. It supports natural language commands for executing web scrapers, managing tasks, and accessing key-value stores.

Provides MCP (Model Control Protocol) tools for accessing and interacting with Google Chat spaces and messages through OAuth2 authentication.

A local MCP server that lets compatible agents use the official, signed Computer Use broker bundled with the OpenAI ChatGPT macOS app.

An MCP server for doing doing initial app planning and creating a good starting point in Databutton – it starts a new app and generates the initial MVP tasks

FastMCP wrapper that lets Claude app fully control a Hermes Agent instance via remote connector.

A proxy MCP server that aggregates tools from multiple MCP servers and forwards calls to the appropriate server, used with the Metatool App for GUI tool management.

Enables coordinating multiple speculative agent execution paths by tracking milestone validation scores and canceling inferior branches early to reduce inference overhead.