Cao MCP Apps
awslabs/cli-agent-orchestrator
Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman).
Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
Install Setup MCP Server
$ npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nesquikm/mcp-rubber-duck setup-mcp-server --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nesquikm/mcp-rubber-duck.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/setup-mcp-server .claude/skills/setup-mcp-server && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "setup-mcp-server" agent skill from https://github.com/nesquikm/mcp-rubber-duck/tree/master/.claude/skills/setup-mcp-server into .claude/skills/setup-mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-mcp-server", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nesquikm/mcp-rubber-duck/tree/master/.claude/skills/setup-mcp-serverType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nesquikm/mcp-rubber-duck setup-mcp-server --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nesquikm/mcp-rubber-duck.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/setup-mcp-server .agents/skills/setup-mcp-server && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "setup-mcp-server" agent skill from https://github.com/nesquikm/mcp-rubber-duck/tree/master/.claude/skills/setup-mcp-server into .agents/skills/setup-mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-mcp-server", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nesquikm/mcp-rubber-duck setup-mcp-server --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nesquikm/mcp-rubber-duck.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/setup-mcp-server .cursor/skills/setup-mcp-server && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "setup-mcp-server" agent skill from https://github.com/nesquikm/mcp-rubber-duck/tree/master/.claude/skills/setup-mcp-server into .cursor/skills/setup-mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-mcp-server", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nesquikm/mcp-rubber-duck.git --path .claude/skills/setup-mcp-server--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nesquikm/mcp-rubber-duck setup-mcp-server --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nesquikm/mcp-rubber-duck.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/setup-mcp-server .gemini/skills/setup-mcp-server && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "setup-mcp-server" agent skill from https://github.com/nesquikm/mcp-rubber-duck/tree/master/.claude/skills/setup-mcp-server into .gemini/skills/setup-mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-mcp-server", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nesquikm/mcp-rubber-duck setup-mcp-serverInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nesquikm/mcp-rubber-duck.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/setup-mcp-server .github/skills/setup-mcp-server && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "setup-mcp-server" agent skill from https://github.com/nesquikm/mcp-rubber-duck/tree/master/.claude/skills/setup-mcp-server into .github/skills/setup-mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-mcp-server", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nesquikm/mcp-rubber-duck setup-mcp-server --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nesquikm/mcp-rubber-duck.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/setup-mcp-server .opencode/skills/setup-mcp-server && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "setup-mcp-server" agent skill from https://github.com/nesquikm/mcp-rubber-duck/tree/master/.claude/skills/setup-mcp-server into .opencode/skills/setup-mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setup-mcp-server", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
setup-mcp-server- GitHub stars
- 178
- Token cost
- ~1.3k tokens
- SKILL.md length
- 578 words
- Files
- 4 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
- Works in 8 steps: Determine target tool → Detect platform → Detect install method → …
- Tasks that involve MCP servers
- SKILL.md covers Reference, Supported tools and config paths, 1. Determine target tool and 2. Detect platform, plus 7 more sections
- Calls claude, node and npx; needs OPENAI_API_KEY and GEMINI_API_KEY
What it does
Setup MCP Server is an agent skill from nesquikm/mcp-rubber-duck. Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/provider-env-vars.md`, `references/tool-configs.md` and `references/troubleshooting.md`).
It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol, Visual Studio Code and OpenAI. The repository describes itself as: An MCP server that acts as a bridge to query multiple OpenAI-compatible LLMs with MCP tool access. Just like rubber duck debugging, explain your problems to various AI "ducks"… The licence is MIT.
When your agent uses it
- Tasks that involve MCP servers
Example prompts
- “/setup-mcp-server”
Requirements
- Node.js
- A credential in OPENAI_API_KEY
- A credential in GEMINI_API_KEY
- Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, AskUserQuestion
Workflow steps
8 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 4e321d9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditBashAskUserQuestion
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
claudenodenpx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
OPENAI_API_KEYGEMINI_API_KEYGROQ_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Setup MCP Server loads about 1.3k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 30 tokens; SKILL.md has 578 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Write, Edit, Bash, AskUserQuestion
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from nesquikm/mcp-rubber-duck at commit 4e321d9, republished under its MIT licence (© nesquikm). 578 words, ~1,252 tokens.
Download SKILL.mdSave it as
.claude/skills/setup-mcp-server/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- setup-mcp-server
- description
- Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
- allowed-tools
- Read, Write, Edit, Bash, AskUserQuestion
- disable-model-invocation
- true
- argument-hint
- [tool-name]
Setup mcp-rubber-duck
You are setting up mcp-rubber-duck as an MCP server in an AI coding tool.
Reference
.claude/skills/setup-mcp-server/references/tool-configs.md— per-tool JSON/YAML config templates.claude/skills/setup-mcp-server/references/provider-env-vars.md— env var reference.claude/skills/setup-mcp-server/references/troubleshooting.md— common issues
Supported tools and config paths
| Tool | Config File (macOS) | Key | Notes |
|---|---|---|---|
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json | mcpServers | Windows: %APPDATA%\Claude\claude_desktop_config.json |
| Claude Code (user) | ~/.claude.json | mcpServers | Prefer claude mcp add CLI |
| Claude Code (project) | .mcp.json | mcpServers | Shared via VCS |
| Cursor (project) | .cursor/mcp.json | mcpServers | |
| Cursor (global) | ~/.cursor/mcp.json | mcpServers | |
| Windsurf | ~/.codeium/windsurf/mcp_config.json | mcpServers | Supports ${env:VAR} |
| VS Code | .vscode/mcp.json | servers | Different key name! Uses ${env:VAR} |
| Continue | .continue/config.yaml | mcpServers (array) | YAML format |
ChatGPT supports MCP via UI only (Developer Mode > Add MCP Server), not a config file.
1. Determine target tool
If $ARGUMENTS specifies a tool name, use it. Otherwise ask the user:
Supported tools: claude-desktop, claude-code, cursor, windsurf, vscode, continue
2. Detect platform
Run uname -s to detect macOS / Linux / Windows (Git Bash). This affects config file paths.
3. Detect install method
Check in order:
which mcp-rubber-duck— if found, usemcp-rubber-duckas the command- If we're inside the mcp-rubber-duck repo (check for
package.jsonwith"name": "mcp-rubber-duck"), offer from-source vianode dist/index.js - Default to
npx -y mcp-rubber-duck
4. Ask about providers
Ask the user which providers to include. Offer these choices:
- OpenAI (
OPENAI_API_KEY) — most popular - Google Gemini (
GEMINI_API_KEY) - Groq (
GROQ_API_KEY) — fast inference - Ollama (local, no key needed)
- CLI agents (Claude CLI, Codex, Gemini CLI, Aider)
Allow multiple selections.
5. Ask about API keys
For each selected HTTP provider that needs a key, ask: provide a real key now or use a placeholder to fill in later?
- If real key: validate it looks reasonable (starts with expected prefix like
sk-for OpenAI,gsk_for Groq) - If placeholder: use descriptive placeholders like
your-openai-api-key-here
6. Load reference templates
Read the config template from .claude/skills/setup-mcp-server/references/tool-configs.md to get the exact JSON/YAML structure for the target tool.
7. Write the configuration
For Claude Code (claude-code)
Use the claude mcp add CLI command — this is the idiomatic way:
claude mcp add --scope user rubber-duck -- mcp-rubber-duckThen set env vars by editing ~/.claude.json to add the env block, or suggest the user set them in their shell profile.
If the user prefers project-scope, use --scope project (writes to .mcp.json).
Show full SKILL.md (220 more words)Show less
For all other tools
- Determine the config file path (platform-aware) from the reference templates
- Read the existing config file if it exists
- If
rubber-duckentry already exists, warn the user and ask before overwriting - If other MCP servers exist, merge — never overwrite the entire file
- If the file doesn't exist, create it (and parent directories with
mkdir -p) - If existing JSON is invalid, warn and offer to backup the broken file before writing
- Write the final config
Important details
- Always include
"MCP_SERVER": "true"in the env block — this is required - VS Code uses
"servers"key, not"mcpServers"— get this right - Continue uses YAML with
mcpServersas an array of objects - Windsurf & VS Code support
${env:VAR_NAME}syntax for env var interpolation
8. Print verification steps
After writing the config, tell the user:
- Restart the tool (fully quit and relaunch for desktop apps)
- Test by using the
list_duckstool withcheck_health: true - Troubleshoot — point them to
.claude/skills/setup-mcp-server/references/troubleshooting.mdif anything goes wrong
Important rules
- Never overwrite existing MCP server entries for other servers
- Always create parent directories before writing config files
- Use the exact JSON structure from the reference templates
- For env var interpolation tools (VS Code, Windsurf), prefer
${env:VAR}syntax over hardcoded keys - Include
DEFAULT_PROVIDERset to the first selected HTTP provider
© nesquikm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in .claude/skills/setup-mcp-server of nesquikm/mcp-rubber-duck.
- SKILL.md
- references/provider-env-vars.md
- references/tool-configs.md
- references/troubleshooting.md
Open the folder on GitHubat commit 4e321d9
Compare with similar skills
Setup MCP Server next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Setup MCP Server this skillnesquikm/mcp-rubber-duck | 178 | — | ~1.3k | Automated safety check: Notes | MIT | |
| Cao MCP Appsawslabs/cli-agent-orchestrator | 1.4k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| UI Widget Developermicrosoft/work-iq | 1k | — | ~6.1k | Automated safety check: Notes | Custom licence | |
| Xquik MCPXquik-dev/x-twitter-scraper | 209 | 1 repos | ~997 | Automated safety check: Pass | MIT | |
| External AgentsBuilderIO/agent-native | 7.1k | — | ~7.2k | Automated safety check: Notes | None | |
| Codex with ChatGPT Planning LoopXiaoDuoYa/codex-with-chatgpt | 7.1k | — | ~11k | Automated safety check: Notes | MIT |
Similar skills
- Official
- Official
UI Widget Developer
microsoft/work-iq
Build MCP servers for Copilot Chat using the OpenAI Apps SDK or MCP Apps SDK widget rendering support (any language).
Xquik MCP
Xquik-dev/x-twitter-scraper
Connect, verify, and troubleshoot Xquik's remote MCP server.
External Agents
BuilderIO/agent-native
Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native…
Codex with ChatGPT Planning Loop
XiaoDuoYa/codex-with-chatgpt
Uses ChatGPT in the browser as the planning and review brain for a Codex session, with Codex keeping all execution and ChatGPT reading the workspace through a bridge.
Chatgpt Apps
Haohao-end/openagent
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI.
More from nesquikm/mcp-rubber-duck
Tool Review
nesquikm/mcp-rubber-duck
Review an MCP tool implementation for correctness, pattern adherence, and best practices.
Update Pricing
nesquikm/mcp-rubber-duck
Update LLM pricing data for all providers. An agent skill from nesquikm/mcp-rubber-duck.
Related
Categories
Questions about Setup MCP Server
What does Setup MCP Server do?
Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.). Setup MCP Server is an agent skill from nesquikm/mcp-rubber-duck.
When should I use Setup MCP Server?
Setup MCP Server fits situations like: tasks that involve MCP servers.
How do I install Setup MCP Server in Claude Code?
Run `npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a claude-code`. Or copy the skill folder (.claude/skills/setup-mcp-server in nesquikm/mcp-rubber-duck) into .claude/skills/setup-mcp-server in your project. Claude Code loads it when a task matches its description.
How do I install Setup MCP Server in Codex?
Run `npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a codex`. Or copy the skill folder (.claude/skills/setup-mcp-server in nesquikm/mcp-rubber-duck) into .agents/skills/setup-mcp-server in your project. Codex loads it when a task matches its description.
Can I use Setup MCP Server in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nesquikm/mcp-rubber-duck --skill setup-mcp-server -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setup-mcp-server, .gemini/skills/setup-mcp-server, .github/skills/setup-mcp-server and .opencode/skills/setup-mcp-server in your project.
What does Setup MCP Server need to run?
Going by SKILL.md and its folder, Setup MCP Server needs the command-line tools its instructions call (claude, node and npx) and credentials named OPENAI_API_KEY, GEMINI_API_KEY and GROQ_API_KEY. Our summary lists: Node.js; A credential in OPENAI_API_KEY; A credential in GEMINI_API_KEY. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, AskUserQuestion.
Does Setup MCP Server access the network?
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Setup MCP Server safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Setup MCP Server use?
Setup MCP Server is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Setup MCP Server use?
About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.
What are the alternatives to Setup MCP Server?
Skills that share tags, products or a category with Setup MCP Server: Cao MCP Apps (awslabs/cli-agent-orchestrator, 1.4k stars), UI Widget Developer (microsoft/work-iq, 1k stars), Xquik MCP (Xquik-dev/x-twitter-scraper, 209 stars) and External Agents (BuilderIO/agent-native, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Setup MCP Server?
nesquikm (a GitHub user) maintains it in nesquikm/mcp-rubber-duck, which has 178 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 5, 2026.
Source: nesquikm/mcp-rubber-duck on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.