New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

MCP Install Helper

by a-streetcoder in a-streetcoder/agent-deck

A skill your agent uses when helping users install, import, repair, or verify MCP server configurations in Agent Deck.

MITAuto-check passedAgent Workflows

Install MCP Install Helper

skills CLI
$ npx skills add a-streetcoder/agent-deck --skill mcp-install-helper -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install a-streetcoder/agent-deck mcp-install-helper --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/a-streetcoder/agent-deck.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-deck/bundled-skills/mcp-install-helper .claude/skills/mcp-install-helper && rm -rf skills-src

Use ~/.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/

Facts

Skill name
mcp-install-helper
GitHub stars
118
Token cost
~1.4k tokens
SKILL.md length
629 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when helping users install, import, repair, or verify MCP server configurations in Agent Deck.

  • Works in 4 steps: ~/.config/mcp/mcp.json → ~/.pi/agent/mcp.json — the app-owned… → /.mcp.json → …
  • Helping users install
  • SKILL.md covers Agent Deck MCP model, Workflow, Direct editing from chat and Field mapping cheatsheet, plus 2 more sections
  • Calls python3, claude and codex; reaches mcp.context7.com; needs CONTEXT7_API_KEY and API_KEY

What it does

MCP Install Helper is an agent skill from a-streetcoder/agent-deck. Use when helping users install, import, repair, or verify MCP server configurations in Agent Deck.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The licence is MIT.

When your agent uses it

  • Helping users install
  • Verify MCP server configurations in Agent Deck

Example prompts

  • “/mcp-install-helper”

Requirements

  • Python 3
  • Node.js
  • Docker
  • A credential in API_KEY
  • A credential in YOUR_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. ~/.config/mcp/mcp.json
  2. ~/.pi/agent/mcp.json — the app-owned writable file
  3. /.mcp.json
  4. /.pi/mcp.json

What it can do on your machine

Read from SKILL.md and the folder at commit 9efbe6c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3
    • claude
    • codex

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • mcp.context7.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • CONTEXT7_API_KEY
    • API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP Install Helper loads about 1.4k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 629 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 passed

The automated check found no risky patterns in SKILL.md.

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 a-streetcoder/agent-deck at commit 9efbe6c, republished under its MIT licence (© a-streetcoder). 629 words, ~1,400 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-install-helper/SKILL.md (or your agent's skills folder).
name
mcp-install-helper
description
Use when helping users install, import, repair, or verify MCP server configurations in Agent Deck.

MCP Install Helper

Use this skill when the user wants to add, import, fix, or test an MCP server for Agent Deck.

Agent Deck MCP model

Agent Deck reads MCP servers from these files, lowest-to-highest precedence:

  1. ~/.config/mcp/mcp.json
  2. ~/.pi/agent/mcp.json — the app-owned writable file
  3. <project>/.mcp.json
  4. <project>/.pi/mcp.json

The MCP view writes only to ~/.pi/agent/mcp.json. Project files can override servers with the same name. Parent Pi sessions receive MCP access through the single mcp proxy tool when MCP is enabled in Runtime → MCP and the server is assigned/advertised for that project.

Supported server config shape:

json
{
  "mcpServers": {
    "server-name": {
      "command": "npx",
      "args": ["-y", "package-name"],
      "env": { "KEY": "VALUE" }
    }
  }
}

or remote HTTP:

json
{
  "mcpServers": {
    "server-name": {
      "url": "https://example.com/mcp",
      "headers": { "API_KEY": "VALUE" },
      "transport": "http"
    }
  }
}

Agent Deck also imports common pasted formats:

  • full JSON with mcpServers
  • bare server map like { "context7": { ... } }
  • single server object like { "command": "npx", "args": [...] } when the UI can ask for a name
  • simple claude mcp add ... / codex mcp add ... commands

Workflow

  1. Ask for the MCP server docs URL, install snippet, or server name if it is not already provided.
  2. Prefer official docs. Fetch/read the docs when a URL is available.
  3. Identify whether the server supports:
    • remote HTTP/SSE endpoint
    • local stdio command
    • required API keys, tokens, headers, or environment variables
    • optional scopes/features the user requested
  4. Choose the simplest working Agent Deck setup:
    • Prefer remote HTTP when the docs provide a stable URL and headers; it avoids local package/runtime issues.
    • Use local stdio when remote is unavailable, OAuth is unsupported in Agent Deck for that server, or the server must access local files/commands.
  5. Ask only for missing required decisions or secrets. If a secret is optional, say so and provide a placeholder unless the user wants to add it now.
  6. Give the user one copy/paste import block for Agent Deck’s MCP import/edit UI, or write ~/.pi/agent/mcp.json directly if the user asks/approves and the session has file-write tools.
  7. Explain any required follow-up: enable MCP in Runtime → MCP, assign the server to the relevant project/agent if needed, refresh/restart the session, then test with the mcp proxy.
Show full SKILL.md (303 more words)Show less

Direct editing from chat

If the user asks you to install it for them from chat, you may edit ~/.pi/agent/mcp.json directly when write tools are available.

Rules for direct edits:

  • Write only to ~/.pi/agent/mcp.json unless the user explicitly asks for a project-local MCP config.
  • Preserve existing settings, unknown top-level keys, and unrelated servers.
  • Upsert only the named server entry.
  • Do not overwrite a same-named server without warning if it comes from a higher-precedence project file.
  • Do not store secrets unless the user explicitly provides them for this purpose. Prefer placeholders like YOUR_API_KEY or env references like $MY_SERVER_API_KEY when appropriate.
  • After writing, tell the user the exact file path and server name.

A safe shell/Python upsert pattern:

sh
python3 - <<'PY'
import json, os
path = os.path.expanduser('~/.pi/agent/mcp.json')
os.makedirs(os.path.dirname(path), exist_ok=True)
try:
    with open(path) as f:
        root = json.load(f)
except Exception:
    root = {}
root.setdefault('mcpServers', {})['SERVER_NAME'] = SERVER_CONFIG
with open(path, 'w') as f:
    json.dump(root, f, indent=2)
    f.write('\n')
PY

Replace SERVER_NAME with a JSON string and SERVER_CONFIG with a Python dict mirroring the MCP JSON.

Field mapping cheatsheet

For local stdio:

  • UI Command field: executable only, e.g. npx, uvx, docker, node, python
  • UI Arguments field: one argument per line, e.g. -y then @vendor/server
  • UI Environment field: KEY=VALUE one per line
  • JSON: command, args, optional env, optional cwd, optional transport: "stdio"

For remote HTTP:

  • UI URL: the MCP endpoint
  • Headers/environment equivalent: required headers such as Authorization or CONTEXT7_API_KEY
  • JSON: url, optional headers, optional transport: "http"

Do not put a whole shell command in the Command field. For example, use command: "npx" and args ["-y", "@upstash/context7-mcp"], not command: "npx -y @upstash/context7-mcp".

Validation checklist

Before finalizing, verify:

  • The server name is stable, lowercase/kebab-case when possible.
  • Local configs have command as one executable and args as an array.
  • Remote configs have url and any required headers.
  • Required secrets are present, intentionally omitted as placeholders, or referenced through env vars.
  • The config is valid JSON if giving an import block.
  • The user knows whether they still need to assign the server or enable MCP globally.

Example: Context7

Remote HTTP:

json
{
  "mcpServers": {
    "context7": {
      "url": "https://mcp.context7.com/mcp",
      "headers": {
        "CONTEXT7_API_KEY": "YOUR_API_KEY"
      },
      "transport": "http"
    }
  }
}

Local stdio:

json
{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
    }
  }
}

© a-streetcoder, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agent-deck/bundled-skills/mcp-install-helper of a-streetcoder/agent-deck.

Open the folder on GitHubat commit 9efbe6c

Compare with similar skills

MCP Install Helper 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.

MCP Install Helper compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP Install Helper this skilla-streetcoder/agent-deck118—~1.4kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Warp GUI to Agent CLI Migration

    warpdotdev/warp

    Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from a-streetcoder/agent-deck

  • Agent Authoring

    a-streetcoder/agent-deck

    A skill your agent uses when creating or reviewing Agent Deck agents, including frontmatter, tools, supervisor behavior, continuation behavior, and skill assignment.

    118 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed

  • Loop Authoring

    a-streetcoder/agent-deck

    A skill your agent uses when creating, refining, or validating Agent Deck loops, especially to guide users iteratively through loop goal, structure, agents, write target, and safety choices.

    118 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed

  • Prompt Authoring

    a-streetcoder/agent-deck

    Create or improve Agent Deck/Pi prompt templates for reusable parent-session workflows.

    118 GitHub stars~721 tokensUpdated 2 mo ago
    Auto-check passed

  • Skill Authoring

    a-streetcoder/agent-deck

    Create or improve Agent Deck/Pi skills, including where to save them, SKILL.md frontmatter, simple vs modular structure, and validation.

    118 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Categories

Questions about MCP Install Helper

What does MCP Install Helper do?

A skill your agent uses when helping users install, import, repair, or verify MCP server configurations in Agent Deck. MCP Install Helper is an agent skill from a-streetcoder/agent-deck. Use when helping users install, import, repair, or verify MCP server configurations in Agent Deck.

When should I use MCP Install Helper?

MCP Install Helper fits situations like: helping users install; verify MCP server configurations in Agent Deck.

How do I install MCP Install Helper in Claude Code?

Run `npx skills add a-streetcoder/agent-deck --skill mcp-install-helper -a claude-code`. Or copy the skill folder (agent-deck/bundled-skills/mcp-install-helper in a-streetcoder/agent-deck) into .claude/skills/mcp-install-helper in your project. Claude Code loads it when a task matches its description.

How do I install MCP Install Helper in Codex?

Run `npx skills add a-streetcoder/agent-deck --skill mcp-install-helper -a codex`. Or copy the skill folder (agent-deck/bundled-skills/mcp-install-helper in a-streetcoder/agent-deck) into .agents/skills/mcp-install-helper in your project. Codex loads it when a task matches its description.

Can I use MCP Install Helper 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 a-streetcoder/agent-deck --skill mcp-install-helper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-install-helper, .gemini/skills/mcp-install-helper, .github/skills/mcp-install-helper and .opencode/skills/mcp-install-helper in your project.

What does MCP Install Helper need to run?

Going by SKILL.md and its folder, MCP Install Helper needs the command-line tools its instructions call (python3, claude and codex) and credentials named CONTEXT7_API_KEY and API_KEY. Our summary lists: Python 3; Node.js; Docker; A credential in API_KEY; A credential in YOUR_API_KEY.

Does MCP Install Helper access the network?

SKILL.md names 1 domain. In commands or code: mcp.context7.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is MCP Install Helper safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does MCP Install Helper use?

MCP Install Helper 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 MCP Install Helper use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to MCP Install Helper?

Skills that share tags, products or a category with MCP Install Helper: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP Install Helper?

a-streetcoder (a GitHub organization) maintains it in a-streetcoder/agent-deck, which has 118 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 1, 2026.

Source: a-streetcoder/agent-deck on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.