AmoyLab/Unla is a gateway service that turns existing APIs and MCP servers into MCP-compatible endpoints through configuration. It helps individuals and organizations connect legacy services to the Model Context Protocol without changing their code, using Docker deployment and a management interface.
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.
npx agentmods add instructions/amoylab/unla/claude-mdgit clone --depth 1 https://github.com/AmoyLab/UnlaWrote 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.
[](https://agentmods.dev/instructions/amoylab/unla/claude-md)<a href="https://agentmods.dev/instructions/amoylab/unla/claude-md"><img src="https://agentmods.dev/badge/instructions/amoylab/unla/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01278 | $0.01278 |
| Opus 5 | $0.00639 | $0.00639 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
Unla 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 5d 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.
curl http://localhost:5234/health How it starts
The opening of the file, as written. The whole thing — 153 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
Unla is an MCP (Model Context Protocol) Gateway service written in Go with a React/TypeScript web interface. It acts as a lightweight proxy and management layer that converts existing APIs and MCP servers into MCP-compliant services through configuration-driven approaches.
Key Architecture:
- Control Plane:
cmd/apiserver- REST API server for management, configuration, and web UI backend - Data Plane:
cmd/mcp-gateway- MCP proxy gateway handling real-time MCP protocol communication - Web Interface:
web/- React/TypeScript dashboard for configuration and chat
Development Commands
Go Backend
# Run tests
make test
make test-coverage # with coverage report
make test-race # with race detection
# Build all services
make build
# Build specific components
make build-allinone # single container
make build-multi # multi-container
# Run services locally
make run-allinone # single container setup
make run-multi # multi-container setup
# Development - run specific services
go run cmd/apiserver/main.go -c configs/apiserver.yaml
go run cmd/mcp-gateway/main.go -c configs/mcp-gateway.yaml
go run cmd/mock-server/main.go
# Configuration testing
go run cmd/mcp-gateway/main.go test -c configs/mcp-gateway.yaml
Web Frontend
cd web/
pnpm run dev # development server
pnpm run build # production build
pnpm run lint # lint TypeScript/React code
pnpm run preview # preview production build
Key Architecture Components
Service Architecture
- apiserver: Database-backed management API with JWT auth, user/tenant management, OpenAI integration
- mcp-gateway: Stateless proxy service with hot-reloading configs, multiple transport support (SSE, stdio, HTTP)
- Web Dashboard: React SPA for configuration management and MCP chat interface
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.
- 5d ago First seen · 153 lines · 1,278 tokens per session scan A d56eef6bb26e
Unla CLAUDE.md is an instructions file published in the GitHub repository AmoyLab/Unla (2,222 stars, last pushed 8d ago), licensed MIT. It adds 1,278 tokens to every session, about $0.0064 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.
Other instructions, from other repositories
mcphub AGENTS.md
AGENTS.md instructions for samanhappy/mcphub, covering mcphub — agent guide, always apply, project-specific build checks and scoped guides.
agent CLAUDE.md
Claude Code instructions for 1mcp-app/agent, covering claude.md, repository information, development commands, setup and build & run.
mcphub CLAUDE.md
Claude Code instructions for samanhappy/mcphub, a project described as: Self-hosted MCP gateway and management platform for connecting, managing, and operating MCP servers.
director CLAUDE.md
Claude Code instructions for fdmtl/director, covering claude.md, product overview and development workflow, quality standards and workflow, engineering excellence and library documentation lookup.
mcp-scribe CLAUDE.md
Instructions for The-Swarm-Corporation/mcp-scribe, covering claude.md, what this is, commands, formatting: black only. do not run ruff format and architecture.
peta-core CLAUDE.md
Claude Code instructions for dunialabs/peta-core, covering claude.md, project overview, core architecture, socket.io real-time communication and user api endpoints.