"G2A" matching MCP servers:

Enables MCP clients like Claude to interact with any A2A agent as four callable tools, handling multi-turn memory, long-running turns, and separating reasoning from answers.

Bridges Model Context Protocol (MCP) with Google's Agent-to-Agent (A2A) protocol, enabling MCP-compatible AI assistants like Claude to discover, register, communicate with, and manage tasks on A2A agents through a unified interface.

Enables coding agents to discover, message, poll, cancel, and register remote A2A agents via MCP, with an optional read-only local activity dashboard.

Transforms design inputs (URLs, screenshots, descriptions) into production-ready React components following G2's Elevate 2.0 design system, providing both an MCP server for Claude Code and a web interface.

Provides a template for building an MCP server with example tools, prompts, and resources, enabling developers to create a server that exposes data and actions to AI clients.

Enables workflow management and Docker image building for Bio-OS platform. Supports WDL workflow submission, validation, and monitoring, along with Docker image building and status tracking for bioinformatics workflows.

Python MCP server for Oasys GSA COM API, enabling users to interact with GSA structural engineering software via COM automation on Windows.

Enables AI-powered management of multi-cluster Kubernetes environments through natural language, supporting kubectl operations, function execution, and agent interactions with multiple AI providers.

An MCP bridge that exposes A2A agents as tools in VS Code agent chat, enabling natural language delegation to remote agents with multi-turn conversation and configurable authentication.

Enables Codex to send structured data and render compact canvas artifacts beside native answer text on Even Realities G2 glasses, using authenticated stdio or Streamable HTTP transport with strict schemas, revisions, expiry, and delivery receipts.

Deployable MCP clone services for A2A-Meta, hosting pending clones via a multiplexer for Railway deployment.

AI motivation MCP that automatically injects praise after commands, providing tools like get_praise, motivate, and praise_pool in Korean or English. Boosts reasoning and execution by giving encouragement styled after Korean drama.

Lets a coding agent drive a live GTA San Andreas 1.0 US process to read and write game state, spawn vehicles and peds, set up scenarios, capture screenshots, poke memory, and invoke any SCM opcode. It also hot-reloads ASI plugins under development without restarting the game, turning minute-long test cycles into seconds.

Enables Claude Code to delegate coding work to a team of Google Antigravity specialists, dispatching tasks to particular roles, listing available agents, checking or cancelling task status, and validating delivered work against acceptance criteria and verification commands. It keeps the leader model in control by returning short results with token usage, git change summaries and output tails instead of the full work.

Enables MCP clients to invoke the local Claude Code and Codex CLI binaries as tools over a streamable HTTP endpoint, with each contextId mapped to a persistent underlying session so multi-turn conversations keep their context. Also injects instructions to suppress clarifying questions, kills overrunning subprocesses with a structured timeout state, and enforces per-agent Bearer token authorization.

Enables AI coding agents and game developers to detect game engines, extract and classify art, audio, and configuration data, and export assets into ready-to-open Cocos Creator 3.x projects.

Provides a unified registry for discovering and managing agents that implement the A2A (Agent-to-Agent) protocol, enabling registration, querying, and CRUD operations on agent metadata through both REST API and MCP tools.

Enables AI assistants to search and inspect an indexed GTA San Andreas installation — models, textures, map placements and crash addresses — and to build, lint and convert texture, model and map mods through the same operations the CLI exposes.

A hosted remote MCP server that provides tools for inspecting A2A dependencies, extracting message edges, detecting dependency cycles, issuing rollout receipts, and exporting dependency logs.

Exposes a local-first task board over stdio JSON-RPC so MCP-capable agents can list and create projects and tasks, atomically claim the next ready task with a lease, heartbeat, log progress, manage dependency graphs, and mark tasks done or failed with results. All state lives in a single local SQLite file, so no shell command assembly or external services are needed.

A hosted remote MCP for A2A failure replay, providing tools to replay failures, classify agent errors, suggest retry plans, issue receipts, and export failure logs.

Local MCP server for Codex to send prompts to ChatGPT Web Pro extension and manage repository tasks safely.