unifi-mcp: Instructions file for GitHub Copilot

.github/copilot-instructions.md

unifi-mcp copilot-instructions.md is an instructions file for GitHub Copilot from gordcurrie/unifi-mcp. It costs 2,050 tokens per session, scanned A, original, MIT.

A set of coding instructions for unifi-mcp, a Go server that lets AI agents perform operations on UniFi home-network systems. It explains the project structure and how to inspect UniFi API responses.

In plain words
What is it for?
Use it when adding or changing tools that call UniFi's version-one API. It guides developers to query real endpoints with the required API key and inspect the returned data before defining Go data structures.
Why use it?
It reduces mistakes caused by guessing the shape of API data, especially when the home network uses a self-signed security certificate.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is gordcurrie/unifi-mcp's own configuration. It tells GitHub Copilot how to work on unifi-mcp 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 unifi-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gordcurrie/unifi-mcp. 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/gordcurrie/unifi-mcp/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/gordcurrie/unifi-mcp

Made for: GitHub Copilot.

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 unifi-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gordcurrie/unifi-mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/gordcurrie/unifi-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/gordcurrie/unifi-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/gordcurrie/unifi-mcp/copilot-instructions/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 unifi-mcp copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gordcurrie/unifi-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/gordcurrie/unifi-mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,050 This file is loaded in full into every session.
When invoked 2,050 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02050 $0.02050
Opus 5 $0.01025 $0.01025
Sonnet 5 $0.00410 $0.00410
Haiku 4.5 $0.00205 $0.00205

Measured 10d ago against content hash 222cbe9307c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

unifi-mcp copilot-instructions.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 10d 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.

real endpoint with curl to see the actual field names, types, and nesting.** Do not
.github/copilot-instructions.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions — unifi-mcp

Project Overview

This is an MCP server written in Go that exposes UniFi home network operations as tools, built on the official modelcontextprotocol/go-sdk.

Architecture

cmd/unifi-mcp/main.go          # entrypoint — flags, env vars, server bootstrap
internal/unifi/                # custom UniFi HTTP client package (no third-party UniFi libs)
tools/                         # MCP tool registration

UniFi API — RTFM: Always verify the real response before writing structs

Before defining or modifying any Go struct that maps to a v1 API response, call the real endpoint with curl to see the actual field names, types, and nesting. Do not assume field shape from documentation, legacy API responses, or prior art — the v1 API frequently uses nested objects where flat fields might be expected.

# Probe any v1 endpoint — substitute path and ID as needed
# -k skips TLS certificate verification; required because the UniFi console
# uses a self-signed certificate in this home lab environment.
curl -sk \
  -H "X-API-Key: $UNIFI_API_KEY" \
  "$UNIFI_BASE_URL/integration/v1/sites/$UNIFI_SITE_ID/<resource>/<id>" \
  | python3 -m json.tool

The env vars UNIFI_BASE_URL, UNIFI_API_KEY, and UNIFI_SITE_ID are always set in the dev environment. This costs one curl call and prevents entire phases of work being based on wrong assumptions (e.g. WiFiBroadcast had flat security/isGuest fields invented from the legacy API; the real v1 response has nested securityConfiguration.type, clientIsolationEnabled, network.type, etc.).

Only the v1 API (/proxy/network/integration/v1/sites/{siteID}/...) is used. The legacy API (/api/s/{site}/...) is intentionally not supported — all tools must use v1 paths only.

The base URL is always https://<console-ip>/proxy/network, configured via UNIFI_BASE_URL. The v1 path is appended relative to this base.

The default site is configured via the UNIFI_SITE_ID env var on the unifi.Client struct so tools don't need to require it as a parameter for single-site home lab use. Where a tool accepts an optional site_id, it falls back to the client default.

Read the full file on GitHub · 202 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. 10d ago First seen · 202 lines · 2,050 tokens per session scan A 222cbe9307c8

Subscribe to this mod's changes

unifi-mcp copilot-instructions.md is an instructions file published in the GitHub repository gordcurrie/unifi-mcp (2 stars, last pushed 25d ago), licensed MIT. It adds 2,050 tokens to every session, about $0.0103 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

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 · 7,296 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 · 5,153 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

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

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

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 · 4,469 tokens