A skill for installing and configuring MCP servers, which are programs that give an AI client extra tools. It detects the user's setup, installs or builds the server when needed, writes the client configuration, and checks that it works.

Use it to set up MCP servers for Claude Code or Claude Desktop, including servers obtained from a Git repository.

It removes the need to find the right configuration file or edit JSON by hand, and helps expose missing installation or build problems.

install-mcp — Skill for Claude Code by cogni-work/insight-wave

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add cogni-work/insight-wave

Claude Code

/plugin install cogni-workspace

Made for: Claude Code.

Or install cogni-workspace, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 19 agents.

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/skills/cogni-work/insight-wave/install-mcp/github.svg)](https://agentmods.dev/skills/cogni-work/insight-wave/install-mcp)

Your own site

<a href="https://agentmods.dev/skills/cogni-work/insight-wave/install-mcp"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/install-mcp/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/skills/cogni-work/insight-wave/install-mcp"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/install-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 235 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,284 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00235	$0.03284
Opus 5.5	$0.00094	$0.01314
Sonnet 5.5	$0.00047	$0.00657
Haiku 4.5	$0.00023	$0.00328

Measured 1mo ago against content hash 763b0c2ed018, 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 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.

cogni-workspace/skills/install-mcp/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install MCP

Why This Exists

Plugins in insight-wave depend on MCP servers (Excalidraw for diagrams, Pencil for web rendering, etc.). No plugin declares a server itself. A checked-in declaration asserts machine state the repository cannot guarantee, so on a machine that never installed the server it is spawned at session start and fails visibly. The server is therefore installed on demand and written into the user's own config, which is the one place that can honestly say what is available. Git-based MCPs also need cloning and building, and users of either client used to have to edit that config by hand.

This skill handles the full lifecycle: detect what's needed, install it, configure it for the user's environment, and verify it works. No manual JSON editing required.

Detect Environment

Determine the user's runtime environment — this affects what needs patching:

Locate the config to write. Claude Code reads a user-scope config; Claude Desktop reads its own. Check both:
- Claude Code (all platforms): ~/.claude.json, top-level mcpServers
- Claude Desktop, macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Claude Desktop, Linux: ${XDG_CONFIG_HOME:-~/.config}/Claude/claude_desktop_config.json
- Claude Desktop, Windows: %APPDATA%/Claude/claude_desktop_config.json
Only the top-level mcpServers in ~/.claude.json is user scope. The per-project projects.<path>.mcpServers objects in that same file are local scope — never write there, or the server disappears the moment the user changes directory.
Classify environment:
- Claude Code CLI — needs the git install AND a --target cli write to ~/.claude.json.
- Claude Desktop — needs the git install AND a --target desktop write.
- Both — Desktop config exists alongside CLI usage. Use --target both.

Record the classification as MCP_TARGET, whose only legal values are cli, desktop and both. The write step below sets and consumes it in a single shell — each invocation gets a fresh environment, so an assignment made here would not survive to reach it.

Read the full file on GitHub · 299 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 299 lines · 235 tokens per session scan A 763b0c2ed018

Subscribe to this mod's changes

install-mcp is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 235 tokens to every session and 3,284 once invoked, about $0.0009 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 2026-09-14.

Building agents DevOps and cloud

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.