agentmods.dev

mcp-cli

mcp-cli is a skill for Claude Code, Codex from zonlabs/mcp-ts. It costs 48 tokens per session (1,731 once invoked), scanned A, original, MIT.

A guide for using the MCP CLI, a command-line tool for discovering and calling MCP servers. It covers local and remote servers, authentication, schemas, tool calls, and the gateway process that connects these commands.

In plain words
What is it for?
Use it to check the CLI version, list or search available servers, inspect tool schemas, call tools, authenticate remote connections, and troubleshoot gateway errors.
Why use it?
It prevents common setup and troubleshooting mistakes, such as using the wrong gateway state or adding remote servers to the wrong configuration file.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 23repo changed 12d ago A scan SkillSpector: warn 48 tokens original MIT

Good fit Use it to check the CLI version, list or search available servers, inspect tool schemas, call tools, authenticate remote connections, and troubleshoot gateway errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zonlabs/mcp-ts/mcp-cli
View source ↗ zonlabs/mcp-ts app.linkos.in
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.

Any agent
npx skills add zonlabs/mcp-ts --skill mcp-cli
Clone the repo
git clone --depth 1 https://github.com/zonlabs/mcp-ts

Made for: Claude Code, Codex.

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-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/zonlabs/mcp-ts/mcp-cli/github.svg)](https://agentmods.dev/skills/zonlabs/mcp-ts/mcp-cli)
Your own site
<a href="https://agentmods.dev/skills/zonlabs/mcp-ts/mcp-cli"><img src="https://agentmods.dev/badge/skills/zonlabs/mcp-ts/mcp-cli/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.

agentmods 80×15 button for mcp-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/zonlabs/mcp-ts/mcp-cli"><img src="https://agentmods.dev/badge/skills/zonlabs/mcp-ts/mcp-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,731 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 115
    Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.
    Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
How audits are shown
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 5.1 $0.00048 $0.01731
Opus 5.5 $0.00019 $0.00692
Sonnet 5.5 $0.00010 $0.00346
Haiku 4.5 $0.00005 $0.00173

Measured 12d ago against content hash 0b06f5041981, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-cli scanned grade A with 1 finding 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 12d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { execFile } from "node:child_process";
skills/mcp-cli/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP CLI (mcpa | mcp-ts)

Overview

Use this skill for every task that invokes mcpa or mcp-ts. CLI 0.3.0 has one gateway: serve runs it in the foreground with live logs, while daemon start runs the same gateway in the background.

Normal list, search, schema, and call commands always use that gateway. They reuse a healthy managed or foreground gateway and auto-start the managed daemon when the gateway is stopped.

Remote MCP catalog

The CLI connects to the hosted gateway at https://mcp.linkos.in for authenticated access to remote MCP servers. Users manage those connections at https://app.linkos.in/mcp?tab=apps.

Servers connected or disconnected in the LinkOS app are synchronized automatically with the running CLI gateway and become available or unavailable in the remote catalog. Do not add app-managed remote servers to local mcp.json, and do not restart a healthy gateway to pick up connection changes. Use mcpa list --tools to inspect the current combined local and remote catalog.

Mandatory preflight

Complete these checks before MCP work:

  1. Resolve the executable and print its version.
    • PowerShell: Get-Command mcpa,mcp-ts -ErrorAction SilentlyContinue, then mcpa --version.
    • POSIX: command -v mcpa || command -v mcp-ts, then mcpa --version.
    • Pin that resolved executable or an explicit local node .../dist/bin/mcp-ts.js entrypoint for the whole session.
  2. If neither executable exists, stop and request approval to install @mcp-ts/cli or download it with npx. Never install or download silently.
  3. Require CLI version 0.3.0 or newer. If it is older, stop and request an upgrade; do not use pre-0.3.0 flags or behavior as a compatibility path.
  4. Run mcpa daemon status and follow the state table below.
  5. Run mcpa list --tools with the same pinned CLI. Verify the expected local and remote catalog before choosing a tool.
  6. If a remote server is missing because the session is absent or expired, run mcpa login, then repeat mcpa list --tools. Authentication failures are not gateway failures; do not restart the gateway to repair auth.

Read the full file on GitHub · 137 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. 12d ago Changed · +2 lines 0b06f5041981
  2. 1mo ago Changed 4cc9c568b07e
  3. 1mo ago First seen · 135 lines · 48 tokens per session scan A 97bee09a4eb6

Subscribe to this mod's changes

mcp-cli is a skill published in the GitHub repository zonlabs/mcp-ts (23 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 1,731 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DebuggingTypeScriptag-ui-protocolagentsmcp-appmcp-clientredis
Related

Other skills, from other repositories

agents-sdk-typescript-debugging

Use when troubleshooting an agent built with the Microsoft Agents SDK (@microsoft/agents-hosting and related packages). Trigger on any of these symptoms: build or TypeScript errors, crashes on startup, 401 or auth errors on incoming requests, the bot not responding to messages, .env configuration problems, Azure AD…

microsoft/Agents · 125 tokens

recover-from-failure

How to recover when a tool call fails — diagnose, not blindly retry.

cacheplane/dawnai · 15 tokens

dawn

Build AI agents and workflows with the Dawn framework — the TypeScript meta-framework for LangGraph. Use when creating, editing, or debugging a Dawn app (routes, tools, state, agents, workflows, testing, deployment).

cacheplane/dawnai · 48 tokens

harn-diagnostics

Use for Harn diagnostics, looking up any HARN- error code, the full code index/catalog, explain output, repair metadata, and fix application safety.

burin-labs/harn · 37 tokens

harn-probe

Choose the cheapest probe that can falsify a consequential codebase or runtime claim.

burin-labs/harn · 21 tokens

harn-rules

Use for authoring and running declarative structural rules — patterns, lint diagnostics, and codemods.

burin-labs/harn · 26 tokens