MCP integration for Claude Code plugins
Wire Model Context Protocol servers into Claude Code plugins — stdio, SSE, HTTP and WebSocket transports, .mcp.json config, OAuth and token auth, tool naming and security practices
- What
- Wire Model Context Protocol servers into Claude Code plugins — stdio, SSE, HTTP and WebSocket transports, .mcp.json config, OAuth and token auth, tool naming and security practices
- Cost
- Free
- Needs
- Claude Code installed (the skill guides wiring MCP servers into its plugins) — the skill is guidance the agent follows, not software
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Selected by Skill Harbor — short listing (the repo states no license, so no content is reproduced): Anthropic's official MCP-integration skill from the claude-code plugin-dev plugin — the complete guide to connecting Model Context Protocol servers to Claude Code plugins. Covers the two config methods (dedicated `.mcp.json` at the plugin root vs inline `mcpServers` in plugin.json), the four server types (stdio for local tools, SSE for hosted OAuth services, HTTP for token-auth REST APIs, WebSocket for real-time), environment variable expansion (`${CLAUDE_PLUGIN_ROOT}` for portability, user env vars for secrets), MCP tool naming (`mcp__plugin_<plugin>_<server>__<tool>`) and how to pre-allow them in command frontmatter, lifecycle management, authentication patterns (automatic OAuth, header tokens, stdio env vars), integration patterns (simple tool wrapper, autonomous agent, multi-server plugin), security best practices (HTTPS only, env vars for tokens, specific tools pre-allowed — never wildcards), error handling, performance, local testing with `/mcp` and `claude --debug`, and an implementation workflow. Honest caveats: guidance only — the agent must already run Claude Code; license not stated by the source repo — short listing with a link only, nothing copied. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: Claude Code installed (the skill guides wiring MCP servers into its plugins) — the skill is guidance the agent follows, not software Install "MCP integration for Claude Code plugins" for me. It gives my agent Anthropic's official guide to connecting Model Context Protocol servers to Claude Code plugins: the two config methods (.mcp.json vs inline mcpServers in plugin.json), the four server types (stdio, SSE, HTTP, WebSocket), env var expansion (${CLAUDE_PLUGIN_ROOT}, user env vars for secrets), MCP tool naming (mcp__plugin_<plugin>_<server>__<tool>) and pre-allowing in command frontmatter, lifecycle, authentication patterns (automatic OAuth, header tokens, stdio env), integration patterns, security best practices (HTTPS only, env vars for tokens, never wildcard pre-allows), error handling, local testing (/mcp, claude --debug), and an implementation workflow. IMPORTANT: the repo states no license — fetch from the link only, and reproduce nothing beyond the link. Repository: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/mcp-integration/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "mcp-integration". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. tell the agent which MCP server to integrate and its auth details; nothing else — it's a guide). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.