What is mcpview CLAUDE.md?

Repository instructions for mcpview, a Go terminal application used to explore and debug MCP servers. MCP is a standard way for AI clients to discover and use tools provided by other programs.

Building, running, connecting to, and debugging mcpview, including its interactive explorer and headless proxy modes.

It gives the coding agent the project's purpose, supported run modes, and exact commands, so it can work with the repository without guessing.

How kungfusheep/mcpview configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kungfusheep/mcpview. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kungfusheep/mcpview/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kungfusheep/mcpview

Made for: Claude Code.

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/kungfusheep/mcpview/claude-md/github.svg)](https://agentmods.dev/instructions/kungfusheep/mcpview/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kungfusheep/mcpview/claude-md"><img src="https://agentmods.dev/badge/instructions/kungfusheep/mcpview/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kungfusheep/mcpview/claude-md"><img src="https://agentmods.dev/badge/instructions/kungfusheep/mcpview/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,082 This file is loaded in full into every session.

When invoked 1,082 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.01082	$0.01082
Opus 5.5	$0.00433	$0.00433
Sonnet 5.5	$0.00216	$0.00216
Haiku 4.5	$0.00108	$0.00108

Measured 2mo ago against content hash 24899ca03749, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpview CLAUDE.md scanned grade A with 0 findings 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP Explorer (mcpview) is a terminal UI application for developing and debugging MCP (Model Context Protocol) servers. Written in Go following a single-file architecture pattern, it provides both interactive exploration and headless proxy functionality.

Build and Run Commands

# Build the application
go build -o mcpview .

# Run in explorer mode (default)
./mcpview

# Run in debug mode with live message pane
./mcpview --debug

# Run in stdio proxy mode (headless - no TUI)
./mcpview --proxy --target "python server.py"

# Auto-connect to MCP server
./mcpview --server "python my_server.py"

# Debug mode with auto-connect
./mcpview --debug --server "node server.js"

# Show help
./mcpview --help

# Run directly without building
go run .

# Install dependencies
go mod tidy

# Format code
go fmt .

# Vet code for issues
go vet .

Current Features

Core MCP Client

✅ JSON-RPC 2.0 communication over stdio transport
✅ MCP protocol initialization and tool/resource discovery
✅ Dynamic form generation from JSON schemas (string, number, boolean, array, object)
✅ Tool execution with parameter validation
✅ Message logging with timestamps and direction tracking

Terminal UI (Bubbletea)

✅ Connection screen for server command input
✅ Tools list browser with navigation
✅ Tool detail view with three-pane layout:
- Tool info (dynamic height based on description)
- Parameter form (scrollable, resizable)
- Response viewer (scrollable, with execution history)
✅ Resources list browser
✅ Message history viewer with pretty-printed JSON
✅ Debug mode with split-pane layout (messages top, tools bottom)

Stdio Proxy Mode

✅ Headless transparent proxy between MCP client and server
✅ Message interception and logging
✅ Automatic target server process management
✅ Works with any MCP client (Claude Desktop, etc.)

Read the full file on GitHub · 155 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.

2mo ago First seen · 155 lines · 1,082 tokens per session scan A 24899ca03749

Subscribe to this mod's changes

mcpview CLAUDE.md is an instructions file published in the GitHub repository kungfusheep/mcpview (5 stars, last pushed 1y ago), licensed Apache-2.0. It adds 1,082 tokens to every session, about $0.0043 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging mcp mcp-tools

mcpview CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcpview CLAUDE.mdkungfusheep/mcpview	Instructions file	5	1y ago	Apache-2.0	A	1,082	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcpview: Instructions file for Claude Code