mcp-gway

mcp-gway is a skill for Claude Code, Codex from deuriib/mcp-gateway. It costs 51 tokens per session (1,958 once invoked), scanned A, original, MIT.

A command-line tool for registering and managing MCP servers. MCP servers are programs that provide tools or data for an AI assistant to use.

In plain words
What is it for?
Use it to configure server connections, choose available tools, set environment values or headers, handle supported sign-in settings, and start the gateway service.
Why use it?
It avoids manually editing server settings and provides one place to add, remove, inspect, update, refresh, list, or run servers. It can manage both local and remote servers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Use it to configure server connections, choose available tools, set environment values or headers, handle supported sign-in settings, and start the gateway service.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deuriib/mcp-gateway/mcp-gway
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 deuriib/mcp-gateway --skill mcp-gway
Clone the repo
git clone --depth 1 https://github.com/deuriib/mcp-gateway

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-gway

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/deuriib/mcp-gateway/mcp-gway"><img src="https://agentmods.dev/badge/skills/deuriib/mcp-gateway/mcp-gway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,958 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.
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 $0.00051 $0.01958
Opus 5 $0.00026 $0.00979
Sonnet 5 $0.00010 $0.00392
Haiku 4.5 $0.00005 $0.00196

Measured today against content hash f26c7ee19e5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-17, from the pricing page.

Security

Grade A, and why

mcp-gway 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://127.0.0.1:8080/health | jq
skills/mcp-gway/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-gway CLI — v2.2.0

Standalone Python CLI (mcp-gway = "mcp_gway.cli:main"). OpenCode format only. Registry (servers/*.json + servers/*.pyi) is the single source of truth.

Commands (9)

Command Signature (from src/mcp_gway/cli.py)
add mcp-gway add <name> --type local|remote [flags]
remove mcp-gway remove <name>
update mcp-gway update <name> --tools <csv> (--tools required)
list mcp-gway list
inspect mcp-gway inspect <name>
serve mcp-gway serve [--transport stdio|http|sse] [--host 127.0.0.1] [--port 8080] [--log-level LEVEL] [--registry-dir PATH] (default stdio; --host/--port only with http|sse)
refresh mcp-gway refresh [<name>] [--auth] [--oauth-port <port>]
mcp mcp-gway mcp [--log-level LEVEL] [--registry-dir PATH] — DEPRECATED hidden alias: serve --transport stdio equiv mcp (mismo loop NDJSON y mismos args a _serve_stdio, modulo aviso de deprecacion en stderr solo mcp); prefer command: [mcp-gway, serve, --transport, stdio] for OpenCode type: local
local-unrestricted mcp-gway local-unrestricted enable|disable|status — break-glass marker 72h (0o600), explicit only

add — full flags (13, cli.py:45-95)

--type (required, click.Choice(["local","remote"])), --url, --command, --tools (default "*"), --env KEY=VALUE (repeatable), --header KEY=VALUE (repeatable, remote only), --oauth-client-id, --oauth-client-secret, --oauth-scope, --timeout (int, default 5000 ms), --enabled/--no-enabled (default enabled), --oauth-port (int, default 8989), --cwd.

# Remote — transport auto-detected (streamable-http → sse → http)
mcp-gway add youtube --type remote --url https://api.example.com/mcp
mcp-gway add supabase --type remote --url https://mcp.supabase.com/mcp --header "Authorization=Bearer TOKEN"
mcp-gway add supabase --type remote --url https://mcp.supabase.com/mcp --oauth-client-id ID --oauth-client-secret SECRET --oauth-scope "openid profile"
mcp-gway add api --type remote --url https://api.example.com/mcp --timeout 10000 --enabled
mcp-gway add api --type remote --url https://api.example.com/mcp --timeout 10000 --no-enabled

# Local — --command is ONE string, split via shlex
mcp-gway add filesystem --type local --command "npx -y @anthropic/mcp-filesystem"
mcp-gway add tools --type local --command "python -m my_mcp_server" --env MY_VAR=value --cwd /path/to/workdir

Read the full file on GitHub · 107 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. today Changed f26c7ee19e5c
  2. yesterday Changed · +11 lines · +5 tokens per session 13143ec4b06f
  3. 5d ago First seen · 96 lines · 46 tokens per session scan A b63d3c851c1c

Subscribe to this mod's changes

mcp-gway is a skill published in the GitHub repository deuriib/mcp-gateway (0 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,958 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens