"Notion - Productivity and Note-Taking App" matching MCP servers:

Enables Notion AI to read and modify files in a single local PC folder and, in full mode, run commands and Codex, Claude Code, or Gemini CLI agents, with user confirmation for each action.

Enables MCP clients to start new Codex conversations and continue existing threads, exposing codex and codex-reply tools over stdio via the Codex app-server protocol.

Enables Claude Code or any MCP client to delegate hands-on coding work to OpenAI Codex over a persistent app-server process, keeping long-lived threads with follow-ups, async polling, approvals, steering, and interrupts. Supports native code review, resuming existing sessions, structured output, and parallel worktree-isolated tasks.

Bridges MCP clients such as Claude Code and Cursor to independent Codex app-server sessions, letting them start, poll, steer, review, compact, cancel, and answer prompts for asynchronous Codex tasks over local stdio or a remote authenticated WebSocket. Runs read-only by default, with workspace-write sandboxing only when a user explicitly enables it, and reports job status, model listing, and progress back to the client.

Generates compiled Flutter apps from JSON Product Requirements Documents. Exposes endpoints for PRD validation, schema, payment terms, and build status.

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.

Enables local development and prototyping of MCP apps with UI views for Portkey Mission Control, using Durable Object storage and a skill for end-to-end building.

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.

An AI-agent-first framework for building MCP servers that deliver interactive React widgets directly within AI chat interfaces like ChatGPT and Claude. It includes automated visual testing and a zero-config local development environment designed for autonomous agent workflows.

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.

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.

Delegate tasks from Claude Code to other models (Codex CLI, DeepSeek, OpenRouter, etc.) without leaving the app.

Enables AI assistants to interact with iOS Simulators and Android Emulators, allowing autonomous app development, UI interaction, profiling, and debugging through natural language.

A local MCP bridge that lets a compatible host start, monitor, steer, interrupt, resume, and approve Codex app-server work while enforcing repository-root security.

Enables coding agents to install and manage Paydirt's iOS SDK for user feedback, trial cancellation, and subscription cancellation, with Slack integration and app building.

An MCP server that reverse-engineers a rebuild spec (CLAUDE.md, config, and mutation-tested tests) from an existing app, enabling coding agents to rebuild the app cleanly against that spec.

Two-way MCP bridge between Claude and Codex: send prompts into a live Codex Desktop thread and messages into a running Claude Code session, keeping each conversation in its own app. Native Desktop tasks on Windows and macOS; CLI/app-server mode on Linux and WSL.

MCP server for Emergent.sh that enables AI assistants to create, monitor, and interact with full-stack app projects, including responding to agent questions and taking preview screenshots.

Lets AI coding agents ask a Rails app about itself: 35 read-only tools answer from the schema, models, routes, controllers, views, jobs and conventions, over MCP or the command line, even when the app cannot boot.

An open engine that gives AI persistent, reusable UI components with a writable component registry, versioned data storage, and a shell runtime, enabling AI to create, save, and reuse single-purpose apps.

A desktop MCP service that integrates voice assistants into Mac workflows, enabling Obsidian memory, app control, Claude Code sessions, pending actions, and multi-language HTTP access.

MCP server that lets Claude, ChatGPT, or VS Code build a complete, machine-checked model of your domain and generate an app from it.

Connect an AI assistant to aCelery, describe the app you want in plain words, and it writes the app, creates its database, runs it on your phone, checks for errors and fixes them — while you watch.

Remote MCP server for Amika: manage sandboxes and agent sessions from any MCP client, including Claude mobile app.

Lets Claude Code and Claude Desktop delegate tasks to Google Antigravity on Windows, running headless CLI jobs with command approval, token tracking, and exported markdown results. Optionally runs tasks as real conversations inside the Antigravity desktop app so they can be watched and opened there.

Connects the ChatGPT web app to a locally running Codex agent over OAuth-secured MCP so users can plan in chat while their own machine reads authorized project files, applies SHA-guarded edits, and runs sandboxed tests. Per-project grants can be revoked anytime, and every write is backed up, conflict-checked, and audited.

dev-brain-mcp

A personal MCP bridge that lets ChatGPT drive a local Codex CLI, translating instructions into Codex app-server threads and returning compact summaries of what Codex did.

Enables AI clients to coordinate coding agents on the user’s own computers and servers over MCP, connecting to Herdr, Codex app-server, and experimental ZCode/Amp connectors through a self-hosted relay without inbound ports.

Exposes an MCP server to claude.ai through an authenticated Cloudflare Tunnel, letting users drive their Claude Code agents by voice from the Claude app. It authenticates requests and forwards tool calls to a LAN-only agent bridge that runs herdr commands against an allowlisted projects folder.

Enables coding agents to turn a natural-language app wish into a routed tech stack, technical contract, design tokens, tracked implementation and test evidence, and a delivery report with a fulfillment certificate. It centralizes reproducible triage, routing, spec, design, status, and delivery workflows for wish-driven app development.

Enables Doubao Work to submit, monitor, resume, and independently verify coding tasks that a local Codex app-server executes in persistent project sessions, with SQLite-backed task state and artifacts retained on the user's machine.

Enables coding agents to query real SF Symbol names from the local SF Symbols app on Mac, helping generate valid SwiftUI/UIKit code without guessing.

Enables three-layer Codex-to-DeepSeek coordination with project memory, task dispatch, worker collection, and workspace permission mapping through an MCP bridge over Codex app-server and Harness.

Bridges Notion AI models to coding environments like OpenCode, Claude Code, and Codex CLI, enabling local file operations and shell commands via MCP tools.

Enables autonomous coding agents to escalate complex technical questions to ChatGPT Desktop app via ToS-compliant UI automation, returning expert responses automatically without user intervention.

Enables Claude Code and Cowork to delegate coding tasks over Remote MCP to isolated Cloudflare Container sandboxes that push work branches and open Draft PRs, with tools for task polling, steering, cancellation, and optional web search and fetch. It authenticates users through a GitHub App and supports long-running task status, results, and budget controls.

Lets a coding agent hand a plain-language app idea to a hosted AI software team that shapes, designs, builds, tests and deploys it, returning a one-time link into the full build workspace. Also lists your apps with their stage, pending approvals and live addresses after a standard OAuth sign-in.

Enables MCP clients to drive Codex Desktop and codex-app-server through durable asynchronous operations for long-running tasks, with polling, approvals, Plan Mode workflows, retry-safe submission, and structured final reports.

Enables MCP-compatible hosts such as OpenCode to drive the Codex CLI through codex app-server over stdio, exposing tools to run prompts, inspect status, list threads, and interrupt running turns.