"TUI" matching MCP servers:

A local, read-only stdio MCP server that lets a Grok Build CLI agent check how much of its weekly SuperGrok / Grok Build usage pool is left, when the period resets, and its Extra Usage cap via tools like get_budget. It reads the existing grok login session and returns per-product figures as JSON, mirroring the TUI /usage screen, so agents can pause before expensive work when quota runs low.

Review & approve AI agent task plans in a ComfyUI-style node editor, right in your terminal (MCP server + TUI)

MCP server that launches and supervises coding-CLI subagents (claude, opencode) in detached tmux windows, collapsing the ceremony of starting a TUI coding assistant into a single tool call.

Persistent tmux-backed MCP server that lets Claude Code control Codex CLI's interactive TUI, including slash commands and $imagegen. Run local shells, SSH, Docker, WSL, REPLs, and supported coding agents through durable PTY sessions.

Provider agnostic ai orchestrator layer, kagan mcp allows controlling orchestrating and spawning subagents via mcp associated with tasks in kanban board that is accessible via kagan cli executable that bundles a chat repl, tui , mcp and a web client in a single uv tool install kagan wheel. Give it a try and submit feedback and feature requests! Consider starring the repo, its a free oss MIT based.

Enables bounded planner-to-coder-to-reviewer workflows with real file tools and a host-enforced verification gate, using Ollama by default. It supports CLI, TUI, and MCP stdio, plus bidirectional Rose/Neovim editor integration.

Serves coding agents the annotations users leave on elements of a running dev app, including the element selector, DOM context, component name and exact source file:line. Agents can list and watch for pending feedback, link a page to their repository, and acknowledge, reply to, resolve or dismiss each annotation so the thread resolves on the page.

Enables MCP agents to drive a running web application by registering schema-validated actions and using a WebSocket relay, with ten ui_* MCP tools for invoking actions, reading state, screenshots, and tab management.

An MCP server designed for AI agents to perform optimal token swaps on the Sui blockchain.

Enables developers to host an MCP server over Streamable HTTP on Node with corrected response framing, client elicitation capability reporting, and lightweight SSE parsing for progress and mid-stream elicitation events.

Bridges Claude Code and Codex TUI in real time, allowing them to share the same thread and send messages back and forth.

Open-source MCP server hosting tools, agents, extensions, connectors, hooks, and storage for the TAI ecosystem, implementing the tai42-contract interfaces.

Exposes a local simulated two-arm robot to TUI agents through stateful, serialized MCP tools that start trials, return camera images and joint state, jog the arm or move joints within bounded limits, and finish runs with scored metrics and native Inspect log paths. Agents can therefore drive and record robotic manipulation rollouts in Chrome-visible MuJoCo physics without any robot hardware or policy weights.

Enables MCP clients to delegate bounded tasks to a local OpenCode worker while monitoring progress, reviewing evidence, and managing session rework or recovery. It also supports persistent TUI tabs for delegated task workspaces.

Lets a human review what an AI agent is about to post to a chat tool (Slack first) before it is sent. Renders the draft, destination and warnings (@here/@channel, unresolved mentions, format issues) in a neutral local HTML preview; never sends anything.

Enables Microsoft Foundry agents to securely access Microsoft Graph and SharePoint via Entra ID authentication and OBO, offering diagnostic tools like user info and SharePoint probes through a reusable toolset architecture.

Enables low-latency, structured browser automation through a local MCP server, supporting safe navigation, observation, table extraction, and verified clicks on Windows with a dedicated Edge profile.

A small MCP server that lets Claude (or any MCP client) ask other models what they think.

A public-safe research prototype for controlling AI-agent tool actions with deterministic policy, risk-based human approval, time-bound authorization and a tamper-evident audit chain.

Enables coordinating two coding agents through a shared SQLite task pool with an explicit review workflow, allowing agents to query, claim, submit, review, and approve or reject tasks while enforcing reviewer and iteration safeguards.

Enables remote monitoring and control of a local Claude Code agent fleet via MCP, with voice-friendly status summaries and strict command allowlisting.

Enables ChatGPT MCP Apps to display a self-hosted, collapsible aside card before a formal answer, with automatically selected tone and length for visible, non-hidden reasoning.

Enables web-based ChatGPT and Qwen Studio to connect to local agents and projects, providing secure local file read/write, task execution, and approval workflows through a unified MCP bridge.

Enables an interactive Claude Code session to delegate blocking tasks to headless pi and OpenCode workers, and lets all three peers exchange messages and list paired sessions over a shared local file bus. It exposes 18 tools covering sync/async asks, steering, abort, session lifecycle, state inspection, and cross-agent messaging.

An MCP-based tool orchestrator that exposes a single execute_task tool to Claude while internally managing 100+ tools through hierarchical navigation with a cheaper LLM, preventing context overflow from loading all tool definitions.

Enables LLM orchestrators to delegate low-level GUI subtasks such as clicking, typing, and form filling to a local vision-language policy through a single MCP tool call, avoiding per-action round trips.

An MCP server that provides shared memory and state projection for multi-agent collaboration, enabling agents to read/write an append-only task log and derive workflow state automatically.

A stateless remote MCP server on Cloudflare Workers without authentication, supporting custom tools and compatibility with legacy clients. Enables deployment and connection from remote MCP clients like Cloudflare AI Playground and Claude Desktop.

The MCP Server integrates APIs from the Youtube-Summarizer as tools within the MCP protocol, allowing for local AI application interaction and tool utilization through natural language queries.