What is install-mcp AGENTS.md?

Repository instructions for a command-line tool that installs and manages MCP servers across different AI clients. MCP, or Model Context Protocol, is a way for AI applications to connect to tools and data sources.

Use them when building, running, testing, linting, or changing the tool's installation and client-support code.

They explain the supported development commands and where installation logic, client configuration, and tests live.

How supermemoryai/install-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to supermemoryai/install-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/supermemoryai/install-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/supermemoryai/install-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/supermemoryai/install-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/supermemoryai/install-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/supermemoryai/install-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/supermemoryai/install-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/supermemoryai/install-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/supermemoryai/install-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,867 This file is loaded in full into every session.

When invoked 2,867 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02867	$0.02867
Opus 5.5	$0.01147	$0.01147
Sonnet 5.5	$0.00573	$0.00573
Haiku 4.5	$0.00287	$0.00287

Measured 1mo ago against content hash a2427ab98842, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

install-mcp AGENTS.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 1mo 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.

AGENTS.md · 473 lines

How it starts

The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Claude Code (claude.ai/code) and similar coding agents when working with code in this repository.

Development Commands

bun run build - Build the project using tsup
bun run build:watch - Build with watch mode
bun run start - Run the CLI locally using ts-node
bun run start:node - Run the built CLI from dist/
bun run test - Run bun test suite
bun run test:watch - Run tests in watch mode
bun run lint - Run Biome linter
bun run lint:fix - Run Biome linter with auto-fix
bun run format - Check code formatting with Biome
bun run format:fix - Auto-format code with Biome
bun run compile - Type-check with TypeScript compiler

Architecture Overview

This is a CLI tool for installing and managing MCP (Model Context Protocol) servers across different AI clients. The tool supports 14+ AI clients with different configuration formats and file locations.

Core Entry Points

bin/run.ts - Main CLI entry point using yargs for command parsing
bin/run - Shell script that requires the built version

Core Components

src/commands/install.ts - Main install command logic handling URL and command-based installations
src/client-config.ts - Client configuration management with platform-specific paths
src/detect-transport.ts - Transport detection logic (stdio, sse, etc.)
src/logger.ts - Logging utilities using consola
src/index.ts - Command registration and CLI setup

Client Support System

Currently Supported Clients (14 total)

Desktop Applications:

Claude Desktop (claude-desktop)
Cursor (cursor)
Windsurf (windsurf)
Witsy (witsy)
Enconvo (enconvo)

VS Code Extensions:

Cline (cline)
Roo-Cline (roo-cline)
VS Code native (vscode)

CLI Tools:

Warp (warp) - Outputs config for manual copy-paste
Gemini CLI (gemini-cli)
Claude Code (claude-code)
Goose (goose)
Zed (zed)
Codex (codex)

Configuration Formats Supported

Read the full file on GitHub · 473 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.

1mo ago First seen · 473 lines · 2,867 tokens per session scan A a2427ab98842

Subscribe to this mod's changes

install-mcp AGENTS.md is an instructions file published in the GitHub repository supermemoryai/install-mcp (197 stars, last pushed yesterday), licensed MIT. It adds 2,867 tokens to every session, about $0.0115 per session on Opus 5.5. 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 2026-08-30.

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 · 9,715 tokens

install-mcp: Instructions file for Codex