What is mcp-tui AGENTS.md?

Instructions for mcp-tui, a terminal interface for discovering and connecting to MCP servers. MCP servers provide tools that an AI assistant can call.

Use them when changing server discovery, configuration parsing, connection screens, tabs, keyboard focus, or automatic connections.

They document the interface, supported configuration formats, keyboard navigation, validation, and connection behavior so changes match the current design.

mcp-tui AGENTS.md — Instructions file for Codex and OpenCode by standardbeagle: Instructions for mcp-tui, a terminal interface for discoveri

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/standardbeagle/mcp-tui/agents-md

Clone the repo

git clone --depth 1 https://github.com/standardbeagle/mcp-tui

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/standardbeagle/mcp-tui/agents-md.svg)](https://agentmods.dev/instructions/standardbeagle/mcp-tui/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/standardbeagle/mcp-tui/agents-md"><img src="https://agentmods.dev/badge/instructions/standardbeagle/mcp-tui/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,029 This file is loaded in full into every session.

When invoked 2,029 The same file — it is already loaded in full.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.02029	$0.02029
Opus 5	$0.01014	$0.01014
Sonnet 5	$0.00406	$0.00406
Haiku 4.5	$0.00203	$0.00203

Measured 5d ago against content hash 66fd2301f4fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-tui AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. **Verify server compatibility**: 以 curl 試 HTTP/SSE。

AGENTS.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

此檔示 Claude Code (claude.ai/code) 於本倉作業之準則。

Recent Updates (2025-01-12) - v0.2.0 Release

本案已成革命性 UI 改善，MCP-TUI 益便用、實用。

Major Features Added

Tabbed Navigation System: 視覺 tabs；以 arrow key 於 Saved/Discovery/Manual modes 間巡行。
File Discovery Engine: 自尋 Claude Desktop、VS Code MCP、MCP-TUI configuration files。
Combined Command Input: 預設單行輸入如 "brum --mcp"；按 'C' 切換。
Enhanced Connection Management: 視覺 connection cards，具 server enumeration 與 descriptions。
Smart Input Priority: Form fields 先於 UI navigation keys。

Key Technical Improvements

MCP Validation: 僅示含實際 MCP server configurations 之 JSON files。
Multi-Format Support: 兼 Claude Desktop、VS Code MCP、native formats。
Enhanced Navigation: 修 focus issues，通體改 keyboard navigation。
Server Enumeration: 自 discovered files 顯 individual server names 與 descriptions。

Key Files Modified

internal/tui/models/connections.go - 增 file discovery 與 server enumeration。
internal/tui/screens/connection.go - 革新 tabbed interface 與 navigation。
internal/tui/app/manager.go - Auto-connect functionality。
internal/tui/screens/main.go - Navigation focus fixes。
examples/ - 完備 configuration examples。

Project Overview

MCP-TUI，Go 製 Model Context Protocol (MCP) servers 測試客戶端；兼 interactive Terminal User Interface (TUI) mode 與 scriptable Command Line Interface (CLI) mode。支援 stdio、SSE、HTTP transports；可 browse/interact MCP servers，execute tools/resources/prompts。

Development Commands

Build

# Build the binary
go build -o mcp-tui .

# Build and install to ~/.local/bin
./build.sh

Run Tests

# Run all tests
go test ./...

# Run tests with coverage
go test -cover ./...

# Run specific test
go test -run TestName

Lint

# Install golangci-lint if not present
go install github.com/golangci-lint/golangci-lint/cmd/golangci-lint@latest

# Run linter
golangci-lint run

# Format code
go fmt ./...

Architecture

Core Components

Read the full file on GitHub · 232 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 232 lines · 2,029 tokens per session scan A 66fd2301f4fc

Subscribe to this mod's changes

mcp-tui AGENTS.md is an instructions file published in the GitHub repository standardbeagle/mcp-tui (11 stars, last pushed 1mo ago), licensed MIT. It adds 2,029 tokens to every session, about $0.0101 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents ai-tools anthropic bubbletea claude cli debugger

mcp-tui AGENTS.md