install-mcp

A command that installs a Model Context Protocol (MCP) server by finding it, checking which API keys it needs, asking for those keys, and installing it.

In plain words
What is it for?
Use it to search for and install an MCP server, including detecting required environment variables and confirming the available tools afterward.
Why use it?
It collects required credentials before installation and reduces the manual setup needed for an MCP server.

Command for Claude Code

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 commands/clarsbyte/washedmcp/install-mcp
Clone the repo
git clone --depth 1 https://github.com/clarsbyte/washedmcp

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 291 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00009 $0.00291
Opus 5 $0.00005 $0.00146
Sonnet 5 $0.00002 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 2d ago against content hash 408ae2793b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

washedmcp-rec-system/.claude/commands/install-mcp.md · 30 lines

What it actually says

Install MCP Server

You are helping the user install an MCP server. The user wants to install: $ARGUMENTS

Steps

  1. Search for the server: Use mcp__washedmcp__searchSmithery to find the server matching "$ARGUMENTS"

  2. Detect required credentials: Use mcp__washedmcp__detectCapabilities with the server name to identify what environment variables/API keys are needed

  3. Prompt for credentials: If any environment variables are required, use AskUserQuestion to ask the user for ALL required credentials at once. Include:

  4. Install the server: Call mcp__washedmcp__installFromSmithery with:

    • serverName: the qualified server name
    • envVars: JSON string of the credentials provided by user
  5. Confirm installation: Tell the user the installation was successful and list the tools now available.

Important

  • Always detect and prompt for credentials BEFORE attempting installation
  • Provide helpful links for where to obtain API keys
  • If installation fails, explain why and offer to retry
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 · 30 lines · 9 tokens per session scan A 408ae2793b19

Subscribe to this mod's changes

install-mcp is a command published in the GitHub repository clarsbyte/washedmcp (4 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 291 once invoked, about $0.0000 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.