mcp

mcp is a command for coding agents from rolecraft-sh/rolecraft. It costs 0 tokens per session (1,211 once invoked), scanned A, original, MIT.

A command group for managing MCP servers used by AI agents. MCP, or Model Context Protocol, lets an agent connect to external tools and data sources.

In plain words
What is it for?
Use it to install, list, search, check, update, and remove MCP servers from sources such as npm, GitHub, Python, Go, Deno, and Rust.
Why use it?
It keeps server installation and maintenance in one workflow instead of requiring separate setup for each agent.

Command

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/rolecraft-sh/rolecraft/mcp
Clone the repo
git clone --depth 1 https://github.com/rolecraft-sh/rolecraft

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 mcp

README.md
[![agentmods](https://agentmods.dev/badge/commands/rolecraft-sh/rolecraft/mcp.svg)](https://agentmods.dev/commands/rolecraft-sh/rolecraft/mcp)
Your own site
<a href="https://agentmods.dev/commands/rolecraft-sh/rolecraft/mcp"><img src="https://agentmods.dev/badge/commands/rolecraft-sh/rolecraft/mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,211 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 $0.00000 $0.01211
Opus 5 $0.00000 $0.00606
Sonnet 5 $0.00000 $0.00242
Haiku 4.5 $0.00000 $0.00121

Measured 4d ago against content hash 9f752726aba8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

docs/commands/mcp.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rolecraft mcp — MCP Server Management

Install, list, search, check, update, and remove MCP servers for AI agents.

Usage

rolecraft mcp install <source> [options]
rolecraft mcp list [options]
rolecraft mcp search <query> [options]
rolecraft mcp check
rolecraft mcp update <source> [options]
rolecraft mcp remove <name> [options]

Subcommands

install

Install an MCP server from a source. Automatically scans gh: sources for security issues before installing.

# npm / npx
rolecraft mcp install npm:@modelcontextprotocol/github --cursor --claude

# npm with version pinning
rolecraft mcp install npm:@modelcontextprotocol/[email protected] --cursor

# GitHub
rolecraft mcp install gh:github/github-mcp-server --all

# GitHub with branch/tag pinning
rolecraft mcp install gh:github/github-mcp-server@main --all
rolecraft mcp install gh:github/[email protected] --cursor

# Python (uvx)
rolecraft mcp install uvx:@anthropic/postgres-mcp --cursor

# Python (pipx)
rolecraft mcp install pipx:postgres-mcp --cursor

# Go
rolecraft mcp install go:github.com/org/mcp-server --all

# Deno
rolecraft mcp install deno:jsr:@org/mcp-server --all

# Rust
rolecraft mcp install cargo:my-mcp-server --cursor

# Local path
rolecraft mcp install ./local-server.js --cursor

# Dry-run
rolecraft mcp install npm:@anthropic/postgres-mcp --all --dry-run

# Custom name
rolecraft mcp install npm:@test/mcp --name my-server --cursor

Options:

  • --name <name> — Override the server name (default: auto-detected from source)
  • --dry-run — Preview without making changes
  • --yes, -y — Skip confirmation and security blocks
  • --agents, --cursor, --claude, --copilot, --continue, etc. — Target specific agents
  • --all — Install to all supported MCP agents

update

Reinstall an MCP server, refreshing to the latest version (or a specified version).

# Update to latest
rolecraft mcp update npm:@modelcontextprotocol/github --cursor

# Update to a specific version
rolecraft mcp update npm:@modelcontextprotocol/[email protected] --cursor

# Update and change target agents
rolecraft mcp update npm:@modelcontextprotocol/github --cursor --claude

# Dry-run
rolecraft mcp update npm:@modelcontextprotocol/github --dry-run

Read the full file on GitHub · 178 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. 4d ago First seen · 178 lines · 0 tokens per session scan A 9f752726aba8

Subscribe to this mod's changes

mcp is a command published in the GitHub repository rolecraft-sh/rolecraft (75 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,211 tokens. 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.