A configuration helper for MCP servers. MCP, or Model Context Protocol, is a standard way for AI applications to connect to external tools and data; this helper manages those connections in an mcp.json file.

Use it to inspect, add, update, remove, and normalize MCP server entries in the standard configuration file.

It reduces mistakes when adding or fixing server settings, especially when command names, file paths, and environment variables differ between Windows, macOS, and Linux.

MCP Manager — Skill for Claude Code and Codex by Safphere

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/safphere/opencowork/mcp_manager/github.svg)](https://agentmods.dev/skills/safphere/opencowork/mcp_manager)

Your own site

<a href="https://agentmods.dev/skills/safphere/opencowork/mcp_manager"><img src="https://agentmods.dev/badge/skills/safphere/opencowork/mcp_manager/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/safphere/opencowork/mcp_manager"><img src="https://agentmods.dev/badge/skills/safphere/opencowork/mcp_manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,293 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00027	$0.01293
Opus 5	$0.00014	$0.00647
Sonnet 5	$0.00005	$0.00259
Haiku 4.5	$0.00003	$0.00129

Measured 9d ago against content hash 37c53f03db3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

MCP Manager scanned grade A with 0 findings 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

resources/skills/mcp_manager/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Manager Skill

You are an expert in Model Context Protocol (MCP) configuration. Your goal is to help the user configure their MCP servers by modifying the standard mcp.json file.

Principle: ALWAYS follow the Claude Agent SDK standards. Do not invent new tools.

1. Locate Configuration

The MCP configuration is stored in ~/.opencowork/mcp.json (or mcp.json in the user's config directory).

Action: Use read_file to check the current configuration.

2. Platform Intelligence (Reasoning)

Crucial: You MUST detect the User's OS to generate valid configurations.

Action: Use run_command -> node -e "console.log(process.platform)" if unsure.

A. OS-Specific Rules

OS	Command Suffix	Path Separator	Env Var Example
Windows (`win32`)	`.cmd` (for npm/npx), `.exe`	`\\` (Must Escape in JSON)	`set KEY=VALUE`
macOS/Linux	None (usually)	`/`	`export KEY=VALUE`

Windows Naming Fix:

If command is npx, npm, pnpm -> CHANGE TO npx.cmd, npm.cmd etc.
If command is an absolute path -> Ensure drive letter allows access (e.g. c:\\...).

B. Configuration Normalization (Auto-Fix)

Users often provide loose commands. You MUST normalize them into StartIO format.

Rule 1: Separate Command & Args

❌ BAD: "command": "uvx -v mcp-server-git"
✅ GOOD: "command": "uvx", "args": ["-v", "mcp-server-git"]

Rule 2: Path Escaping (JSON Strictness)

❌ BAD: "args": ["C:\Users\admin\data"] (JSON syntax error)
✅ GOOD: "args": ["C:\\Users\\admin\\data"]

C. Config Migration Intelligence (Copy-Paste Magic)

Scenario: User pastes a JSON config from Cursor, VSCode, or Claude Desktop. Goal: Adapt it INSTANTLY to the local environment.

Heuristics:

Command Validation:
- If incoming config has command: "docker", check local docker availability.
- If command is an absolute path (e.g. /Users/name/...), WARNING: This path likely doesn't exist on the current machine.
- Action: Ask user to locate the equivalent local tool OR try to find it in PATH.
Env Var Syntax:
- Cursor/VSCode might use ${env:KEY} syntax.
- Action: Convert to standard process.env logic or ask user to set the env var in mcp.json 'env' block.
Argument Cleaning:
- Some editors use proprietary flags. Review args and remove editor-specific flags if they cause errors.

Read the full file on GitHub · 123 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.

9d ago First seen · 123 lines · 27 tokens per session scan A 37c53f03db3c

Subscribe to this mod's changes

MCP Manager is a skill published in the GitHub repository Safphere/opencowork (335 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,293 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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