How do I install the MCP CLI skill?

Run npx skillmds@latest add romiluz13/mcp-cli in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is MCP CLI safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with MCP CLI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is MCP CLI free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published MCP CLI?

romiluz13 (@romiluz13) published this skill. Their other Agent Skills are listed on their SkillMD profile.

MCP CLI by romiluz13 — Agent Skill

Name: MCP CLI
Rating: 4.5 (4 reviews)
Author: romiluz13

File contents

MCP CLI (Transient MCP Access)

Overview

The mcp CLI (from github.com/f/mcptools) discovers and invokes MCP server capabilities on-demand. Use it when a task needs ONE server's tool — a doc fetch, a single query, a quick lookup — instead of permanently mounting that server as an always-loaded integration.

This keeps accelerators transient: spun up for the task, used, and dropped. A permanently mounted MCP server costs context on every session whether you call it or not. The CLI costs nothing until you run it.

Composes with cc10x:research.

Prerequisite (install once)

Check first: command -v mcp. If absent, install:

git clone https://github.com/f/mcptools /tmp/mcptools
CGO_ENABLED=0 go build -o ~/.local/bin/mcp /tmp/mcptools/cmd/mcptools
# ensure ~/.local/bin is on PATH

If go is unavailable, report that the accelerator is missing and proceed with built-in tools — do NOT treat the missing binary as a task blocker (it is a fallback message, not a wall).

Flow: discover → call → release

1. Discover first — always. Never call a tool whose schema you have not seen — guessed params fail silently or hit the wrong tool.

mcp tools <server-command>                 # list tools
mcp tools --format json <server-command>   # full param schema for parsing
mcp resources <server-command>             # list resources
mcp prompts <server-command>               # list prompts

2. Lead read-only when exploring. Restrict the surface before you touch an unfamiliar server:

mcp guard --allow 'tools:read_*,list_*' --deny 'tools:write_*,delete_*' <server-command>

Drop the guard only once you know exactly which write you intend.

3. Call with params matching the discovered signature exactly (param:str, param:num, [optional]):

mcp call <tool_name> --params '<json>' -f json <server-command>

Output -f json for parsing, -f pretty for reading. Check exit code and stderr on failure — a non-zero exit is a real error, not a fallback message.

Server-command examples:

stdio: npx -y @modelcontextprotocol/server-filesystem /path
HTTP: pass the URL (auto-detected); SSE via --transport sse
auth: --auth-header "Bearer <token>", --auth-user user:pass, or -e ENV_VAR for docker servers

Aliases (only for repeated use in one task)

If you call the same server several times, alias it; remove it when the task ends so nothing lingers:

mcp alias add <name> <server-command>   # then: mcp tools <name>, mcp call ... <name>
mcp alias remove <name>                 # release when done

Aliases persist in ~/.mcpt/aliases.json. Cleaning them up is part of keeping the accelerator transient.

---name: mcp-clidescription: Use when you need a one-off MCP server capability during research or debugging without permanently mounting it as a context-polluting integration.--- # MCP CLI (Transient MCP Access) ## Overview The `mcp` CLI (from `github.com/f/mcptools`) discovers and invokes MCP server capabilities on-demand. Use it when a task needs ONE server's tool — a doc fetch, a single query, a quick lookup — instead of permanently mounting that server as an always-loaded integration. This keeps accelerators **transient**: spun up for the task, used, and dropped. A permanently mounted MCP server costs context on every session whether you call it or not. The CLI costs nothing until you run it. Composes with `cc10x:research`. ## Prerequisite (install once) Check first: `command -v mcp`. If absent, install: ```bash git clone https://github.com/f/mcptools /tmp/mcptools CGO_ENABLED=0 go build -o ~/.local/bin/mcp /tmp/mcptools/cmd/mcptools # ensure ~/.local/bin is on PATH ``` If `go` is unavailable, report that the accelerator is missing and proceed with built-in tools — do NOT treat the missing binary as a task blocker (it is a fallback message, not a wall). ## Flow: discover → call → release **1. Discover first — always.** Never call a tool whose schema you have not seen — guessed params fail silently or hit the wrong tool. ```bash mcp tools <server-command> # list tools mcp tools --format json <server-command> # full param schema for parsing mcp resources <server-command> # list resources mcp prompts <server-command> # list prompts ``` **2. Lead read-only when exploring.** Restrict the surface before you touch an unfamiliar server: ```bash mcp guard --allow 'tools:read_*,list_*' --deny 'tools:write_*,delete_*' <server-command> ``` Drop the guard only once you know exactly which write you intend. **3. Call** with params matching the discovered signature exactly (`param:str`, `param:num`, `[optional]`): ```bash mcp call <tool_name> --params '<json>' -f json <server-command> ``` Output `-f json` for parsing, `-f pretty` for reading. Check exit code and stderr on failure — a non-zero exit is a real error, not a fallback message. **Server-command examples:** - stdio: `npx -y @modelcontextprotocol/server-filesystem /path` - HTTP: pass the URL (auto-detected); SSE via `--transport sse` - auth: `--auth-header "Bearer <token>"`, `--auth-user user:pass`, or `-e ENV_VAR` for docker servers ## Aliases (only for repeated use in one task) If you call the same server several times, alias it; remove it when the task ends so nothing lingers: ```bash mcp alias add <name> <server-command> # then: mcp tools <name>, mcp call ... <name> mcp alias remove <name> # release when done ``` Aliases persist in `~/.mcpt/aliases.json`. Cleaning them up is part of keeping the accelerator transient.

Frequently asked questions

MCP CLI