mcpproxy-go: Instructions file for Claude Code

CLAUDE.md

mcpproxy-go CLAUDE.md is an instructions file for Claude Code from smart-mcp-proxy/mcpproxy-go. It costs 5,867 tokens per session, scanned A, original, MIT.

Project instructions for mcpproxy-go, a Go service that acts as a proxy for model tools and follows autonomous working rules.

In plain words
What is it for?
They guide feature work through failing Go tests, standard formatting, mocked fallbacks for unclear dependencies, and escalation for destructive changes.
Why use it?
They set defaults for making safe assumptions, require test-first progress, and define when work must stop for human input.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is smart-mcp-proxy/mcpproxy-go's own configuration. It tells Claude Code how to work on mcpproxy-go itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcpproxy-go configures →

Reuse

Borrowing it

Nothing to install: this file belongs to smart-mcp-proxy/mcpproxy-go. 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/smart-mcp-proxy/mcpproxy-go/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/smart-mcp-proxy/mcpproxy-go

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.

agentmods badge for mcpproxy-go CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/smart-mcp-proxy/mcpproxy-go/claude-md/github.svg)](https://agentmods.dev/instructions/smart-mcp-proxy/mcpproxy-go/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/smart-mcp-proxy/mcpproxy-go/claude-md"><img src="https://agentmods.dev/badge/instructions/smart-mcp-proxy/mcpproxy-go/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.

agentmods 80×15 button for mcpproxy-go CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/smart-mcp-proxy/mcpproxy-go/claude-md"><img src="https://agentmods.dev/badge/instructions/smart-mcp-proxy/mcpproxy-go/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,867 This file is loaded in full into every session.
When invoked 5,867 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05867 $0.05867
Opus 5.5 $0.02347 $0.02347
Sonnet 5.5 $0.01173 $0.01173
Haiku 4.5 $0.00587 $0.00587

Measured today against content hash b379d9b12cb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpproxy-go 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 today.

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 · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code / AI agents working in this repo. This file is loaded into every session — keep it lean. It is orientation + behavior only; detailed reference lives in docs/.

Project Overview

MCPProxy is a Go desktop application that acts as a smart proxy for AI agents using the Model Context Protocol (MCP): intelligent tool discovery, massive token savings, and built-in security quarantine against malicious MCP servers.

Stack: Go 1.26 (backend) · TypeScript 5.9 / Vue 3.5 (frontend) · Swift 5.9 (macOS tray). Storage: BBolt (config.db) + Bleve (search index). Avoid new dependencies without clear need.

Editions (Personal & Server)

Built in two editions from one codebase via Go build tags:

Edition Build Binary Distribution
Personal (default) go build ./cmd/mcpproxy mcpproxy macOS DMG, Windows installer, Linux tar.gz
Server go build -tags server -o mcpproxy-server ./cmd/mcpproxy mcpproxy-server Docker image (ghcr.io) only — no .deb / tar.gz

All server code is behind //go:build server in internal/serveredition/; the personal edition is unaffected. The binary self-identifies (mcpproxy version, /api/v1/status → "edition"). Server multi-user OAuth (Spec 024): see docs/development/server-edition-multiuser-auth.md.

Every feature decision should ask: "Does this make the personal edition so good that developers tell their teammates about it?"

Architecture

Core + Tray split: mcpproxy (headless HTTP API + MCP proxy) and mcpproxy-tray (GUI that manages the core). The tray is a UI controller — it holds no state; it reads/writes core config via REST + SSE. Tray↔core over a Unix socket (~/.mcpproxy/mcpproxy.sock) / named pipe on Windows; socket connections bypass the API key (OS-level auth), TCP requires it.

Directory Purpose
cmd/mcpproxy/ CLI entry point (Cobra)
cmd/mcpproxy-tray/ System tray app (state machine)
internal/runtime/ Lifecycle, event bus, background services
internal/server/ HTTP server, MCP proxy
internal/httpapi/ REST API (/api/v1)
internal/upstream/ 3-layer client: core/managed/cli
internal/config/ Configuration management
internal/index/ Bleve BM25 search index
internal/storage/ BBolt database
internal/oauth/ OAuth 2.1 + PKCE
internal/security/ Sensitive-data detection + quarantine
internal/serveredition/ Server-only code (//go:build server)
native/macos/MCPProxy/ Swift macOS tray app

Read the full file on GitHub · 162 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.

  1. today Changed · +1 lines · +384 tokens per session b379d9b12cb7
  2. 4d ago Changed · +1 lines · +429 tokens per session 14679a7c440e
  3. 6d ago Changed · +2 lines · +516 tokens per session cbed3185276e
  4. 13d ago Changed · +2 lines · +371 tokens per session 518ac5554a42
  5. 14d ago Changed · +4 lines · +617 tokens per session 120279199582
  6. 16d ago Changed · -2 lines · -111 tokens per session 8e34d1225e89
  7. 24d ago Changed · +1 lines · +179 tokens per session a88104e8bb5b
  8. 25d ago Changed · +1 lines · +149 tokens per session 5eb7643f0613
  9. 26d ago Changed · +19 tokens per session 25990407dc71
  10. 1mo ago First seen · 152 lines · 3,314 tokens per session scan A 155b8cb39174

Subscribe to this mod's changes

mcpproxy-go CLAUDE.md is an instructions file published in the GitHub repository smart-mcp-proxy/mcpproxy-go (399 stars, last pushed today), licensed MIT. It adds 5,867 tokens to every session, about $0.0235 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,786 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens