"Google Pub/Sub" matching MCP servers:

Enables task-specific coding agents defined in Markdown files to be run from any MCP-compatible client, executing them with a chosen coding CLI backend and returning the result to the same conversation. The same agent definitions can be reused across clients with shared backend and model configuration, and continued across multiple calls through sessions.

Lets any MCP-capable AI and a human share a single serial port through one resident daemon, so the AI can read device output, send commands, and drive embedded boards alongside an engineer. It also performs atomic expect→send matching to win sub-second races such as U-Boot countdowns and login prompts, while keeping reads bounded for context hygiene.

Complete Google Ads API v21 MCP server with 40+ fully implemented tools for campaign, ad group, keyword, extension, and portfolio bidding management, enabling AI assistants to create, optimize, and manage Google Ads campaigns through natural language commands.

MCP server that vets LLM-emitted shell commands BEFORE execution — detects rm -rf nested deep in chains, package-manager glob removal (apt remove 'nvidia'), dd/mkfs filesystem destruction, chmod 777 / chown -R privilege blast, network-exfil via curl | bash, chained shutdown/reboot, git destructive ops. 30 detection rules across 8 families. Sub-second, local, free, MCP-native.

Enables OpenAI Codex to delegate tasks to Google Antigravity CLI, running them headlessly and polling for results.

A controlled Model Context Protocol bridge that lets OpenAI Codex delegate work to Google Antigravity CLI on demand, with project-scoped opt-in and read-only delegation.

Lets Codex delegate tasks to the Google Antigravity CLI (agy) with background job execution, live progress tracking, a visual dashboard, and structured error diagnostics.

Enables MCP clients to run Google Antigravity CLI (agy) as durable, detached asynchronous jobs with a permission gate and broker-computed verdicts that do not trust agy's own exit code.

Wraps Google Antigravity CLI into 11 typed MCP tools, enabling any MCP client to invoke agy for code review, prototyping, execution, and long-running tasks.

Local MCP server that exposes delegation tools for Codex, Claude, and Antigravity CLI, enabling an orchestrator agent to assign tasks to these sub-agents via non-interactive CLI commands.

Connects Google Gemini and local workflows to Google Antigravity IDE, enabling skill, plugin, rule, artifact, and transcript inspection along with workspace command execution, runtime workspace switching, and orchestration of local project resources.

Exposes the Antigravity CLI to MCP clients for structured planning, code review, test validation, general prompts, and literal slash commands against Google Gemini models.

Enables MCP hosts to delegate coding tasks to Pi CLI as a programmable sub-agent with session tracking and process management.

Model Context Protocol server for Gmail integration. This allows Claude Desktop (or any MCP client) to interact with your Gmail account through Google Apps Script.

Enables AI assistants to securely connect to and execute commands on a remote Linux server via Cloudflare Tunnel, with bearer-token authentication.

An MCP server that lets Claude Code call the Google Antigravity CLI (agy) headlessly for a second opinion from a different model family, or to have agy read project files on Claude's behalf so large files never enter Claude's context window.

Enables Claude Desktop to execute tasks via the Google Antigravity CLI (agy), exposing its models, skills, plugins, and background workers as native tools.

Exposes the foldkit mesh SDK as MCP tools and resources, enabling natural language interaction with the 7-prime spine, κ-bands, and fold operations.

Integrates Google Gemini AI into Warp terminal workflows through three focused tools: single-turn chat for quick questions, multi-turn conversations with context preservation, and AI-powered code analysis with bug detection and optimization suggestions.

Enables OAuth-capable AI clients to connect to one public HTTPS /mcp endpoint and invoke reviewed, allowlisted commands from registered CLIs such as PocketShell, DataOps, Dapier, and AISL. It supports dynamic discovery, per-CLI OAuth scopes, approval-gated writes, and credential isolation without storing CLI logins in the assistant.

Enables execution of SSH commands on remote servers and management of Google Cloud Platform (GCE) instances through Cursor IDE.

Unified MCP server for managing cloud resources across AWS, Google Cloud, Azure, and DigitalOcean by wrapping their CLI tools.

Enables AI assistants to manage Google Cloud TPU VMs, including queueing, monitoring, bootstrapping, and SSH/tmux integration.

Creates and manages multi-agent teams of AI coding assistants (Claude Code, Codex CLI) that collaborate in tmux terminal sessions. Enables a leader agent to assign sub-tasks to team members for coordinated development.

Enables interaction with Google Cloud Platform services through gcloud CLI commands via a Cloud Run deployed MCP server. Supports executing gcloud commands and managing GCP resources through natural language.

A desktop management platform for plugin management, log querying, service control, and packaging/deployment, with an MCP protocol bridge for AI clients.

Enables MCP clients to drive an installed Path of Building (PoE2) through the full pob command set as tools, allowing agents to read and modify builds, run calculations, search trade, and highlight locations in the PoB interface without modifying it.

Enables a chat agent to drive the official Antigravity CLI headlessly: start and later resume tasks in separate agent contexts, audit what each run actually executed, and complete Google sign-in on a machine with no browser. It also surfaces permission mode and denial hints so a run that silently did nothing is never mistaken for success.

Gives ChatGPT hands-on control of a local machine: reading, patching and executing code in approved project folders, running real interactive processes, managing plans and worker sub-chats, and driving the browser or desktop through user-granted permissions. Every capability is a switch inside an approved-folder sandbox, so nothing runs that the user did not explicitly enable.

Enables AI assistants to securely access and control a Windows machine remotely, running commands and managing files via an MCP server protected by Bearer-token authentication and exposed through a Cloudflare Tunnel.