A command-line toolkit for connecting MCP servers to coding agents. MCP, or Model Context Protocol, is a standard way for an agent to use external tools; the toolkit supports setup, discovery, skills, and health checks.

It helps connect tools to applications such as Claude Code, Cursor, VS Code, and Codex; list or search available servers; create agent skills; and diagnose or update the setup.

It removes the need to hand-edit different configuration files for each coding-agent application. It also provides one place to find, connect, run, and update servers.

umt-mcp — Skill for Claude Code by Markgatcha/universal-mcp-toolkit

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 Markgatcha/universal-mcp-toolkit --skill umt-mcp

Clone the repo

git clone --depth 1 https://github.com/Markgatcha/universal-mcp-toolkit

Made for: Claude Code.

Or install umt, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 3 MCP servers.

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/markgatcha/universal-mcp-toolkit/umt-mcp/github.svg)](https://agentmods.dev/skills/markgatcha/universal-mcp-toolkit/umt-mcp)

Your own site

<a href="https://agentmods.dev/skills/markgatcha/universal-mcp-toolkit/umt-mcp"><img src="https://agentmods.dev/badge/skills/markgatcha/universal-mcp-toolkit/umt-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/markgatcha/universal-mcp-toolkit/umt-mcp"><img src="https://agentmods.dev/badge/skills/markgatcha/universal-mcp-toolkit/umt-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 684 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00089	$0.00684
Opus 5	$0.00044	$0.00342
Sonnet 5	$0.00018	$0.00137
Haiku 4.5	$0.00009	$0.00068

Measured 3d ago against content hash cfc720c986eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-20, from the pricing page.

Security

Grade B, and why

umt-mcp scanned grade B 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| codex | `~/.codex/config.toml` (managed TOML block) |

plugin/skills/umt-mcp/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal MCP Toolkit (UMT)

UMT is a registry of 28+ production-ready MCP servers plus a CLI (umt) that connects them to every major coding harness. Data lives locally; servers run over stdio by default.

Core commands

umt list — enumerate servers with categories and tool counts
umt search <query> — find servers by name, description, or tool name
umt connect — guided flow: pick servers + harness, writes the real config
umt config -s <ids> -t <harness> --write — non-interactive config write
umt skill <ids> — scaffold Agent Skills (.agents/skills/umt-*/SKILL.md) that teach agents when/how to use each server
umt run <id> — launch one server (with optional --supervise)
umt doctor [id] [--fix] — check builds, env vars, and config health
umt update [--check] — self-upgrade the CLI

Prefer umt connect for interactive setup and umt config … --write for scripts. Both merge into the harness's real config file and keep a .umt-bak backup — never ask the user to hand-edit harness JSON.

Harness matrix (`-t/--target`)

Target	Config location
claude-desktop	OS-specific `claude_desktop_config.json`
claude-code	`./.mcp.json` (project scope)
cursor	`~/.cursor/mcp.json`
codex	`~/.codex/config.toml` (managed TOML block)
gemini-cli	`~/.gemini/settings.json`
vscode	`./.vscode/mcp.json` (workspace scope)
windsurf	`~/.codeium/windsurf/mcp_config.json`
zed	OS-specific Zed `settings.json`
opencode	`~/.config/opencode/opencode.json`
cline	VS Code globalStorage `cline_mcp_settings.json`
agents-md	`./AGENTS.md` (managed markdown section)
json	stdout snippet for manual copying

Zero-config servers

hackernews, arxiv, and npm-registry need no environment variables — good defaults for a first setup. Most others need a token (e.g. github needs GITHUB_TOKEN); umt config prints exactly which ones after writing.

When NOT to use

Do not use UMT to run servers the user's harness already configured, and do not create MCP configs by hand — regenerate them with umt config --write instead so existing settings are merged safely.

Read the full file on GitHub · 56 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.

3d ago First seen · 56 lines · 89 tokens per session scan B cfc720c986eb

Subscribe to this mod's changes

umt-mcp is a skill published in the GitHub repository Markgatcha/universal-mcp-toolkit (13 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 684 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.

Building agents LLM ai-tools claude mcp mcp-server model-context-protocol

swag

This skill should be used when the user says "add proxy config", "create reverse proxy", "SWAG config", "nginx proxy", "expose service", "proxy configuration", "subdomain config", "subfolder config", "configure SWAG", "list proxy configs", "view proxy config", "edit proxy config", "remove proxy config", "check proxy…

jmagar/swag-mcp · 118 tokens

hmem-release

Pre-publish checklist for hmem: skills synced, version bumped, tests green, nothing forgotten. Use before npm publish or when the user says 'release', 'publish', 'push a release', or 'neue Version'.

Bumblebiber/hmem · 50 tokens

hmem-migrate-o

Migrate O-entries to the v5.3+ project-bound 5-level structure (each O00XX bound to its P00XX). Use on 'migrate O-entries', when hmem-update flags a structure migration, or when you notice O-entries still in the old flat L2→L4→L5 format.

Bumblebiber/hmem · 76 tokens

hmem-new-rule

Add a new rule and place it correctly — decide between a cross-project R-entry and a project-specific subnode under the active project's Rules section. Use whenever the user says 'neue Regel', 'Regel hinzufügen', 'new rule', 'add a rule', or invokes /hmem-new-rule. Critical safeguard: project-specific rules placed as…

Bumblebiber/hmem · 95 tokens

hmem-new-project

Create a new P-entry (project) in hmem via createproject — handles schema, section setup, and O-entry linking. Use when the user asks to add/register/track a new project ('neues Projekt', 'P-Entry erstellen'), or before any writememory with prefix='P'.

Bumblebiber/hmem · 65 tokens

delegacion-local

Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…

ZahiriNatZuke/local-delegate · 137 tokens

umt-mcp