mcpproxy-go AGENTS.md

Project instructions for mcpproxy-go, a Go proxy with a web interface and optional desktop tray program. They describe its folders, build and test commands, code style, and testing expectations.

In plain words
What is it for?
Use them when changing the proxy daemon, HTTP API, storage, upstream handling, frontend, embedded web files, tray application, or integration and smoke tests.
Why use it?
They help an agent work in the correct part of a mixed Go and Vue project and use the repository's validation commands. They also clarify how to check the core daemon, tray target, web assets, and APIs.

Instructions file for CodexOpenCode

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/smart-mcp-proxy/mcpproxy-go/agents-md
Clone the repo
git clone --depth 1 https://github.com/smart-mcp-proxy/mcpproxy-go

Made for: Codex, OpenCode.

Per session 772 This file is loaded in full into every session.
When invoked 772 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 $0.00772 $0.00772
Opus 5 $0.00386 $0.00386
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 2d ago against content hash ede6b3214f1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcpproxy-go 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 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.

Makes network callslowCapability

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

- `scripts/verify-api.sh` — exercise the `/api/v1` REST surface with curated curl calls.
AGENTS.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

  • cmd/mcpproxy hosts the core daemon entrypoint; cmd/mcpproxy-tray builds the CGO-based tray binary.
  • Runtime logic, HTTP handlers, storage, and upstream orchestration live in internal/ (internal/runtime, internal/httpapi, internal/upstream, internal/storage).
  • Vue/Tailwind assets are kept in frontend/; bundled static output is embedded from web/.
  • Integration and regression assets reside under tests/ and scripts/; Go unit tests sit beside source files.

Build, Test, and Development Commands

  • make build — compile the proxy and tray binaries for the host platform.
  • go build ./cmd/mcpproxy — quick core rebuild; GOOS=darwin CGO_ENABLED=1 go build ./cmd/mcpproxy-tray validates the macOS tray target.
  • npm install && npm run build inside frontend/ — install web deps and emit production assets.
  • scripts/run-web-smoke.sh — spin up the proxy and execute the Playwright smoke suite.
  • scripts/verify-api.sh — exercise the /api/v1 REST surface with curated curl calls.

Coding Style & Naming Conventions

  • Run gofmt (tabs, goimports defaults) on all Go sources; prefer descriptive package-level names (runtime, upstream, storage).
  • TypeScript/Vue files follow Prettier defaults (npm run lint); components use PascalCase.vue, composables use useThing.ts.
  • Configuration and DTO structs live in shared packages (internal/contracts, internal/httpapi); avoid anonymous maps between layers.

Testing Guidelines

  • Unit tests: go test ./internal/... (set GOCACHE/GOMODCACHE to workspace paths when sandboxed).
  • Targeted suites: go test ./internal/server -run TestMCP -v for lifecycle checks; npm run test:unit for frontend units.
  • End-to-end: scripts/run-e2e-tests.sh after ensuring @modelcontextprotocol/server-everything is warmed and reachable.
  • Name Go tests TestFeatureScenario; snapshot or fixture data belong under tests/ with explicit prefixes.

Read the full file on GitHub · 42 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 · 42 lines · 772 tokens per session scan A ede6b3214f1b

Subscribe to this mod's changes

mcpproxy-go AGENTS.md is an instructions file published in the GitHub repository smart-mcp-proxy/mcpproxy-go (326 stars, last pushed 2d ago), licensed MIT. It adds 772 tokens to every session, about $0.0039 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.