agentmods.dev

mcp-server-comparedge copilot-instructions.md

Project instructions for a ComparEdge MCP server that provides structured information about software tools, including prices, features, alternatives, and category rankings. An MCP server is a service that an AI assistant can query through a standard interface.

In plain words
What is it for?
Use it to search software tools, view their profiles and pricing, compare products, find alternatives, detect free plans, or view category rankings.
Why use it?
They explain how to connect the server to VS Code or GitHub Copilot and what information each available query provides. This avoids having to work out the server setup and tool names from scratch.

Instructions file for GitHub Copilot

3 1mo ago A scan 373 tokens original MIT
View the source file comparedge/mcp-server-comparedge
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/comparedge/mcp-server-comparedge/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/comparedge/mcp-server-comparedge

Made for: GitHub Copilot.

Per session 373 This file is loaded in full into every session.
When invoked 373 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 $0.00373 $0.00373
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash 784321cf99c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-comparedge copilot-instructions.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.

.github/copilot-instructions.md · 57 lines

What it actually says

ComparEdge MCP Server — Copilot Instructions

This repository contains the ComparEdge MCP server (@comparedge/mcp-server).

What this server does

Provides structured access to verified SaaS and AI tool data:

  • Pricing plans and tiers for 508+ products
  • Top alternatives and competitor comparisons
  • Feature comparisons and category rankings
  • Free tier detection

Setup in VS Code / GitHub Copilot

Add to your VS Code settings.json to enable Copilot to query ComparEdge data:

{
  "github.copilot.chat.mcp.servers": {
    "comparedge": {
      "command": "npx",
      "args": ["-y", "@comparedge/mcp-server"],
      "type": "stdio"
    }
  }
}

Or via .vscode/mcp.json in your project:

{
  "servers": {
    "comparedge": {
      "command": "npx",
      "args": ["-y", "@comparedge/mcp-server"],
      "type": "stdio"
    }
  }
}

Available tools

  • search_tools — Search by name, category, or keyword
  • get_tool — Full profile: pricing, features, rating
  • compare_tools — Side-by-side comparison of two tools
  • get_pricing — Detailed pricing plans with verified dates
  • get_alternatives — Top verified alternatives for any tool
  • get_leaderboard — Category rankings by rating
  • list_category — All tools in a category, with free_only filter
  • list_categories — All 45 supported categories

Data source

All data is fetched live from comparedge.com. No API key required.

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 · 57 lines · 373 tokens per session scan A 784321cf99c9

Subscribe to this mod's changes

mcp-server-comparedge copilot-instructions.md is an instructions file published in the GitHub repository comparedge/mcp-server-comparedge (3 stars, last pushed 1mo ago), licensed MIT. It adds 373 tokens to every session, about $0.0019 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.

Data and AIResearchclaudemcpmcp-servermodel-context-protocolpricingsaas
Related

Other instructions, from other repositories

unprice AGENTS.md

AGENTS.md instructions for jhonsfran/unprice, covering agent guide, operating principles, repo map, architecture boundaries and zod and type contracts.

jhonsfran/unprice · 2,091 tokens

unprice CLAUDE.md

Claude Code instructions for jhonsfran/unprice, a project described as: Open-source customer money path for usage-based SaaS — authorize customer spend before paid work runs.

jhonsfran/unprice · 4 tokens

llm-context.py CLAUDE.md

Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.

cyberchitta/llm-context.py · 582 tokens

openrouter-mcp-multimodal AGENTS.md

Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 783 tokens

Silex AGENTS.md

AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).

silexlabs/Silex · 1,155 tokens

seekstone CLAUDE.md

Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.

shaqmughal/seekstone · 1,116 tokens