
mcp-installer
Find, install, and configure MCP servers. Use proactively for MCP discovery, OAuth setup, env vars, stdio vs SSE transport, or troubleshooting MCP connections. Examples: - user: "Add the filesystem MCP server" → read server file, add to mcpServers in opencode.json, verify transport type - user: "How do I use MCP with GitHub?" → check catalog, install @modelcontextprotocol/server-github, configure OAuth token - user: "MCP not connecting" → check transport type (stdio/SSE), verify args/command, check env vars are passed - user: "What MCPs are available?" → run listmcps.py, show catalog with auth types and install commands
- Installs
- 184
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/igorwarzocha/opencode-workflows --skill mcp-installer- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads mcp-installer automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
MCP Installer
Find, install, and configure MCP servers for OpenCode.
<workflow>1. Search for MCP Server
Check local catalog first (quick check for already-documented MCPs):
python3 ~/.config/opencode/skill/mcp-installer/scripts/list_mcps.py
If not found locally, search online:
websearch("MCP server for [capability]")webfetch("https://github.com/modelcontextprotocol/servers")- Check npm:
@modelcontextprotocol/server-* - Check the MCP spec repo: https://github.com/modelcontextprotocol
2. Read MCP Details
For relevant matches, read the full MCP file:
references/mcps/<name>.md
Contains installation config, setup, features, and links.
3. Configure
Add the MCP config to user's opencode.json.
4. Document New MCPs
If you discovered a new MCP server online, you MUST document it for future reference in references/mcps/<name>.md using the template below.
5. Setup (if needed)
- OAuth: Run
opencode mcp auth <server-name> - API keys: Set environment variables
- Other: Follow MCP-specific setup steps
<question_tool>
Batching: Use the question tool for 2+ related questions. Single questions → plain text.
Syntax: header ≤12 chars, label 1-5 words, add "(Recommended)" to default.
When to ask: Multiple MCPs match the need, or setup requires OAuth/API keys.
</question_tool>
<configuration>Local MCP
{
"mcp": {
"name": {
"type": "local",
"command": ["npx", "-y", "@package/name"]
}
}
}
Remote MCP
{
"mcp": {
"name": {
"type": "remote",
"url": "https://example.com/mcp"
}
}
}
MCP Tool Management
MCPs expose tools. Control via the permission section using the tool name (usually the MCP name):
Global/Agent Permission:
{
"permission": {
"my-mcp": "deny", // Disable all tools for this MCP
"my-mcp*": "deny" // Wildcard support
}
}
Pattern-based control:
{
"permission": {
"my-mcp": {
"safe_tool": "allow",
"risky_tool": "ask",
"*": "deny"
}
}
}
Legacy Configuration
Agents may occasionally work on legacy projects using outdated configuration fields (e.g., tools:). You MUST correct these to the modern permission: system when encountered.
OAuth
Remote MCPs with OAuth auto-authenticate:
opencode mcp auth <server-name>
Check status: opencode mcp list
<reference_files>
| You need... | Read this file |
|---|---|
| All config options (local, remote, oauth, env vars) | references/configuration.md |
| Common MCP server examples | references/examples.md |
| Troubleshooting issues | references/troubleshooting.md |
Note: The local catalog (list_mcps.py) is a cache of discovered MCPs, not a complete list. SHOULD always search online if you don't find a match locally.
</reference_files>
<documenting_new_mcps>
When discovering new MCP servers, you MUST document them:
Location: references/mcps/<name>.md
Template:
---
name: mcp-name
url: https://github.com/org/repo
type: local|remote
auth: oauth|api-key|none
description: One-line description
tags: [tag1, tag2]
---
# Display Name
Brief description.
## Installation
\`\`\`jsonc
{
"mcp": {
"name": {
"type": "remote",
"url": "https://example.com/mcp"
}
}
}
\`\`\`
## Setup
Steps for auth, env vars, etc.
## Features
- Feature 1
- Feature 2
## Links
- [GitHub](url)
Then run: python3 scripts/list_mcps.py to verify.
Frontmatter Fields
| Field | Required | Purpose |
|---|---|---|
name | Yes | MCP identifier (key in config) |
url | No | Source URL |
type | Yes | local or remote |
auth | Yes | oauth, api-key, or none |
description | Yes | One-liner for catalog |
tags | No | Array of category tags |
</documenting_new_mcps>
FAQ
What does the mcp-installer skill do?
Find, install, and configure MCP servers. Use proactively for MCP discovery, OAuth setup, env vars, stdio vs SSE transport, or troubleshooting MCP connections. Examples: - user: "Add the filesystem MCP server" → read server file, add to mcpServers in opencode.json, verify transport type - user: "How do I use MCP with GitHub?" → check catalog, install @modelcontextprotocol/server-github, configure OAuth token - user: "MCP not connecting" → check transport type (stdio/SSE), verify args/command, check env vars are passed - user: "What MCPs are available?" → run listmcps.py, show catalog with auth types and install commands
How do I install mcp-installer?
Run npx skills add https://github.com/igorwarzocha/opencode-workflows --skill mcp-installer in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/mcp-installer/ (personal) or .claude/skills/mcp-installer/ (project).
Which AI agents can use mcp-installer?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is mcp-installer safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains mcp-installer?
It is published by igorwarzocha in igorwarzocha/opencode-workflows. It has 184 recorded installs.
More from igorwarzocha/opencode-workflows
powerpoint
igorwarzocha/opencode-workflows
Handle PowerPoint (.pptx) creation, design, and analysis. Use for pitch decks, status updates, and visual storytelling. Use proactively when precise layout positioning and design principles are needed. Examples: - user: "Create a 10-slide deck for the board meeting" - use design principles + html2pptx - user: "Convert this report into a presentation" - extract text and map to template - user: "Audit this deck for layout issues" - generate thumbnail grid for inspection
word
igorwarzocha/opencode-workflows
Handle Word document (.docx) creation, editing, and analysis with high-fidelity visual review. Use for professional reports, legal documents, and tracked changes. Use proactively when quality and precise formatting are critical. Examples: - user: "Create a professional report in Word" - use python-docx with render loops - user: "Draft a legal contract with redlines" - use ooxml redlining workflow - user: "Extract text from this DOCX while preserving structure" - use pandoc markdown conversion
security-nextjs
igorwarzocha/opencode-workflows
Review Next.js security audit patterns for App Router and Server Actions. Use for auditing NEXTPUBLIC exposure, Server Action auth, and middleware matchers. Use proactively when reviewing Next.js apps. Examples: - user: "Scan Next.js env vars" → find leaked secrets with NEXTPUBLIC prefix - user: "Audit Server Actions" → check for missing auth and input validation - user: "Review Next.js middleware" → verify matcher coverage for protected routes - user: "Check Next.js API routes" → verify auth in app/api and pages/api - user: "Secure Next.js headers" → audit next.config.js for security headers
create-opencode-plugin
igorwarzocha/opencode-workflows
Create OpenCode plugins using the @opencode-ai/plugin SDK. Use for building custom tools, event hooks, auth providers, or tool execution interception. Use proactively when developing new plugins in .opencode/plugin/ or /.config/opencode/plugin/. Examples: - user: "Create a plugin to block dangerous commands" → implement tool execution before hook with blocking logic - user: "Add a custom tool for jira" → design tool schema and implementation using SDK context - user: "Show toast on file edit" → react to file edit events and display status message - user: "Build a custom auth provider" → implement auth flow for new model provider - user: "Intercept git commits" → add hook to validate commit messages before execution
agent-architect
igorwarzocha/opencode-workflows
Create and refine OpenCode agents via guided Q&A. Use proactively for agent creation, performance improvement, or configuration design. Examples: - user: "Create an agent for code reviews" → ask about scope, permissions, tools, model preferences, generate AGENTS.md frontmatter - user: "My agent ignores context" → analyze description clarity, allowed-tools, permissions, suggest improvements - user: "Add a database expert agent" → gather requirements, set convex-database-expert in subagenttype, configure permissions - user: "Make my agent faster" → suggest smaller models, reduce allowed-tools, tighten permissions
opencode-config
igorwarzocha/opencode-workflows
Edit opencode.json, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables. Examples: - user: "Add Anthropic as a provider" → edit opencode.json providers, add API key baseEnv var, verify with opencode run test - user: "Restrict this agent's permissions" → add permission block to agent config, set deny/allow for tools/fileAccess - user: "Set GPT-5 as default model" → edit global or agent-level model preference, verify model name format - user: "Disable gofmt formatter" → edit formatters section, set languages.gofmt.enabled = false
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available