mcp-rust-proxy CLAUDE.md

Repository instructions for a Rust server that connects clients to multiple Model Context Protocol servers. Rust is a programming language, and MCP is a standard for connecting software agents to tools and data sources.

In plain words
What is it for?
Use it when developing or reviewing the proxy, its server management, transport and protocol layers, shared state, or Yew-based web interface.
Why use it?
It explains how the proxy routes requests, manages server health and connections, supports transport methods, and keeps the project organized across branches.

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/zach-source/mcp-rust-proxy/claude-md
Clone the repo
git clone --depth 1 https://github.com/zach-source/mcp-rust-proxy
Per session 3,279 This file is loaded in full into every session.
When invoked 3,279 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.

ModelPer sessionOnce invoked
Fable 5 $0.03279 $0.03279
Opus 5 $0.01639 $0.01639
Sonnet 5 $0.00656 $0.00656
Haiku 4.5 $0.00328 $0.00328

Measured 3d ago against content hash fd65ac0c02c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-rust-proxy CLAUDE.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 3d 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. Use `curl http://localhost:3001/api/logs/{server}/stream` for raw SSE stream
CLAUDE.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Rust Proxy - Claude Development Guide

Project Overview

MCP Rust Proxy is a high-performance Model Context Protocol (MCP) proxy server built in Rust. It provides connection pooling, health monitoring, and a web UI for managing multiple MCP servers.

Project Structure

  • This is a git work tree folder structure, the root folder has no code; the sub folders are of branches, create branches and merge to main when tested and ready
  • Main development happens in feature branches (e.g., feature/rust-mcp-proxy)

Key Components

Core Architecture

  • Proxy Server (src/proxy/): Handles incoming MCP requests and routes them to appropriate backend servers
  • Server Management (src/server/): Manages MCP server lifecycle, health checks, and restarts
  • Transport Layer (src/transport/): Supports stdio, HTTP-SSE, and WebSocket transports
  • State Management (src/state/): Centralized state using DashMap for thread-safe concurrent access
  • Protocol Version Support (src/protocol/): Multi-version MCP protocol support with automatic translation
  • Web UI (yew-ui/): Rust/WASM frontend built with Yew framework

Protocol Version Support

  • Supported Versions: 2024-11-05, 2025-03-26, 2025-06-18
  • Auto-Detection: Protocol version detected during initialize handshake
  • Bidirectional Translation: Automatic message translation between any version pair
  • Zero-Copy Optimization: Pass-through mode when versions match
  • API Integration: Protocol version visible in /api/servers and /api/servers/{name} responses
  • Structured Logging: Version negotiation logged with structured fields (server_name, protocol_version)
  • Deprecation Warnings: Logs WARN for servers using 2024-11-05 (deprecated)

Aggregator Plugin (Claude Agent SDK Integration)

  • Plugin Location: src/plugins/official/aggregator-plugin.js
  • Rust Integration: src/proxy/aggregator_tools.rs
  • Purpose: Intelligent multi-server context aggregation using Claude to query multiple MCP servers
  • Key Features:
    • Uses @anthropic-ai/claude-agent-sdk to orchestrate queries across multiple MCP servers
    • Enforces MCP tool usage over training data with explicit tool use: [servers] directives
    • Intelligent server selection based on query keywords:
      • context7: Default for documentation/library information
      • serena: Auto-selected for code-related queries (function, class, method, etc.)
      • filesystem: Auto-selected for file operations (file, directory, path, etc.)
      • fetch: Auto-selected for web operations (url, website, http, etc.)
    • Comprehensive logging for debugging tool usage and server selection
    • Tracks aggregation statistics (response sizes, processing time, tool calls)

Read the full file on GitHub · 339 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. 3d ago First seen · 339 lines · 3,279 tokens per session scan A fd65ac0c02c4

Subscribe to this mod's changes

mcp-rust-proxy CLAUDE.md is an instructions file published in the GitHub repository zach-source/mcp-rust-proxy (5 stars, last pushed 10mo ago), licensed MIT. It adds 3,279 tokens to every session, about $0.0164 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 2026-08-31.

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 · 6,785 tokens

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

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