mcp-sync

mcp-sync is a skill for Claude Code, Codex from Shana-AE/.shanaae-configs. It costs 83 tokens per session (2,762 once invoked), scanned B, original, no licence file.

A configuration synchronizer that keeps MCP server settings and enabled states aligned across OpenCode, Claude Code, Codex, and a repository file using one shared source.

In plain words
What is it for?
Use it after changing the shared MCP server list, when tool configurations have drifted, or when you need to enforce one setup across a repository.
Why use it?
It removes differences between the MCP settings used by different coding tools. Changes made in one canonical list can be applied consistently elsewhere.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it after changing the shared MCP server list, when tool configurations have drifted, or when you need to enforce one setup across a repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shana-ae/.shanaae-configs/mcp-sync
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 Shana-AE/.shanaae-configs --skill mcp-sync
Clone the repo
git clone --depth 1 https://github.com/Shana-AE/.shanaae-configs

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-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/shana-ae/.shanaae-configs/mcp-sync/github.svg)](https://agentmods.dev/skills/shana-ae/.shanaae-configs/mcp-sync)
Your own site
<a href="https://agentmods.dev/skills/shana-ae/.shanaae-configs/mcp-sync"><img src="https://agentmods.dev/badge/skills/shana-ae/.shanaae-configs/mcp-sync/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-sync

Your own site · 80×15
<a href="https://agentmods.dev/skills/shana-ae/.shanaae-configs/mcp-sync"><img src="https://agentmods.dev/badge/skills/shana-ae/.shanaae-configs/mcp-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,762 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 unknown 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 $0.00083 $0.02762
Opus 5.5 $0.00033 $0.01105
Sonnet 5.5 $0.00017 $0.00552
Haiku 4.5 $0.00008 $0.00276

Measured yesterday against content hash cc81e3afc067, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mcp-sync 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 yesterday.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/mcp_stdio.py, scripts/patch_dsh_mcp_panel.py, scripts/sync_dsh_connector.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

description: "Synchronize MCP server config and enabled/disabled status across OpenCode, Claude Code (~/.claude.json), Codex (~/.codex/config.toml), and the repo .claude/mcp.json from one canonical source (mcp_servers.js
ai/skills/local/mcp-sync/SKILL.md · 196 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. yesterday Changed · +107 lines cc81e3afc067
  2. 1mo ago Changed · +5 lines 6947cbc4c4a2
  3. 2mo ago First seen · 84 lines · 83 tokens per session scan B 74292d83829b

Subscribe to this mod's changes

mcp-sync is a skill published in the GitHub repository Shana-AE/.shanaae-configs (2 stars, last pushed yesterday), with no licence file. It adds 83 tokens to every session and 2,762 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Related

mcp-sync compared with skills from other repositories

mcp-sync next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-syncShana-AE/.shanaae-configsSkill2yesterdaynoneB83Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code