mcp-proxy-wrapper CLAUDE.md

Repository-specific engineering notes for an MCP Proxy Wrapper, a TypeScript library that places hooks around tool calls made by MCP servers. The hooks can run before or after a tool call and can change its inputs or results.

In plain words
What is it for?
Use them when changing proxy behavior, hook interfaces, logging, tool-call interception, build commands, or tests in the MCP Proxy Wrapper repository.
Why use it?
They explain the library's architecture and conventions so developers can extend the wrapper without first tracing every component and hook interaction.

Instructions file

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/mcp-plugins/mcp-proxy-wrapper/claude-md
Clone the repo
git clone --depth 1 https://github.com/mcp-plugins/mcp-proxy-wrapper
Per session 749 This file is loaded in full into every session.
When invoked 749 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00749 $0.00749
Opus 5 $0.00375 $0.00375
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 2d ago against content hash 5de64db4fccb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-proxy-wrapper 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 2d 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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

This is the MCP Proxy Wrapper - a TypeScript library that provides a hook system for intercepting and modifying tool calls in Model Context Protocol (MCP) servers. The library wraps existing MCP server instances without requiring backend infrastructure changes.

Core Architecture

Main Components

  • src/proxy-wrapper.ts: Core wrapper functionality that intercepts MCP server tool registrations
  • src/interfaces/proxy-hooks.ts: TypeScript interfaces for hooks and configuration
  • src/utils/logger.ts: Logging utility with configurable levels and colored output
  • src/index.ts: Main entry point that exports all public APIs

Hook System

The proxy wrapper implements a hook system with two main phases:

  • beforeToolCall: Executes before tool calls, can modify arguments or short-circuit execution
  • afterToolCall: Executes after tool calls, can modify results

The wrapper intercepts the server.tool() method to inject hook execution around the original tool handlers.

Development Commands

Build and Test

npm run build          # Compile TypeScript to dist/
npm test              # Run Jest test suite
npm run lint          # Run ESLint on TypeScript files
npm run format        # Format code with Prettier

Running Individual Tests

npm test -- src/proxy-wrapper.test.ts              # Run specific test file
node src/proxy-wrapper.simple.test.js              # Run JavaScript test directly

Development Workflow

npm run prepare       # Runs build automatically
npm run prepublishOnly # Runs tests and lint before publishing

Key Technical Details

Module System

  • Uses ES modules ("type": "module" in package.json)
  • TypeScript config targets ES2022 with NodeNext module resolution
  • Jest configured for ESM with ts-jest transform

Dependencies

  • Runtime: @modelcontextprotocol/sdk, zod
  • Development: TypeScript, Jest, ESLint, Prettier
  • Peer Dependencies: @modelcontextprotocol/sdk (must be provided by consuming application)

Read the full file on GitHub · 89 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. 2d ago First seen · 89 lines · 749 tokens per session scan A 5de64db4fccb

Subscribe to this mod's changes

mcp-proxy-wrapper CLAUDE.md is an instructions file published in the GitHub repository mcp-plugins/mcp-proxy-wrapper (5 stars, last pushed 1y ago), licensed MIT. It adds 749 tokens to every session, about $0.0037 per session on Opus 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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 · 6,785 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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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 · 7,296 tokens