MCP Integration for Claude Code Plugins

Name: claude-code/mcp-integration
Author: anthropics

View on GitHub↗

Share on X Share on LinkedIn Share on Bluesky

40Medium

The skill's wildcard `allowed-

ThreatsCI SM CS BC S HITL

Behavior Analysis

Description verified — behavior matches claim

Claims to do

MCP Integration for Claude Code Plugins: Model Context Protocol (MCP) enables Claude Code plugins to integrate with external services and APIs by providing structured tool access. Use MCP integration to expose external service capabilities as tools within Claude Code.

Actually does

This skill provides comprehensive documentation and configuration examples for integrating Model Context Protocol (MCP) servers into Claude Code plugins. It details how to configure `stdio` (executing local commands like `npx`), `SSE` (connecting to HTTPS URLs), `HTTP` (connecting to HTTPS URLs with headers), and `WebSocket` (connecting to WSS URLs with headers) server types. It also covers environment variable usage, security best practices, and debugging steps, but does not execute any commands or contact URLs itself.

Threat Analysis

AI Agent Traps ↗Scanned 4/14/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction1 finding

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Nameanthropics/claude-code/mcp-integration

Registrygithub

Version5c18c787f262

PURLpkg:github/anthropics/claude-code@5c18c787f262?skill=mcp-integration

Stars114,388

Installs455,628

Source

Repository ↗SKILL.md ↗

SHA-2561cbfb6b1cf98...

SHA-1144d8525277c...

MD5bd191bc9925b...

TLSH8a42b71295a9...

ssdeep384:Pp4ijiFm...

Size12,519 bytes

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.

GitHub

https://github.com/anthropics/claude-code/tree/main/skills/mcp-integration

455,628 installs

Claude CodeDocs

/plugin marketplace add anthropics/claude-code

/plugin install mcp-integration@anthropics/claude-code

Skills.shDocs

npx skills add https://github.com/anthropics/claude-code --skill mcp-integration

Assessments (1)

AI Agent Traps ↗

Wildcard tool permissions increase attack surfacemediumautonomy abuse, privilege escalation

The 'allowed-tools' configuration supports wildcards, which, despite being warned against, can grant broad permissions. If an attacker can introduce malicious tools to an MCP server, a wildcard permission could allow the agent to use them, leading to unintended actions or privilege escalation.

80% confidenceline 218

allowed-tools: ["mcp__plugin_asana_asana__*"]

Version History (2)

f348a16da8280None4/15/2026 5c18c787f262current40Medium4/14/2026

Dependencies (13)

agent-sdk-dev.claude-plugin/marketplace.jsonnot scanned

claude-opus-4-5-migration.claude-plugin/marketplace.jsonnot scanned

code-review.claude-plugin/marketplace.jsonnot scanned

commit-commands.claude-plugin/marketplace.jsonnot scanned

explanatory-output-style.claude-plugin/marketplace.jsonnot scanned

feature-dev.claude-plugin/marketplace.jsonnot scanned

frontend-design.claude-plugin/marketplace.jsonnot scanned

hookify.claude-plugin/marketplace.jsonnot scanned

learning-output-style.claude-plugin/marketplace.jsonnot scanned

plugin-dev.claude-plugin/marketplace.jsonnot scanned

pr-review-toolkit.claude-plugin/marketplace.jsonnot scanned

ralph-wiggum.claude-plugin/marketplace.jsonnot scanned

security-guidance.claude-plugin/marketplace.jsonnot scanned

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-code/mcp-integration.svg)](https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-code/mcp-integration)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-code/mcp-integration"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-code/mcp-integration.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-code/mcp-integration.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow