Skip to content

aiskillstore/marketplace / skills/89jobrien/mcp-integration

mcp-integration

Verified

Model Context Protocol (MCP) integration specialist. Use when creating MCP server configurations, implementing MCP integrations, or optimizing MCP performance. Specializes in MCP server architecture and integration patterns.

FileKindSize
SKILL.mdskill md2.8 KB
skill-report.jsonconfig24.0 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T12:52:07.682Z",
    "slug": "89jobrien-mcp-integration",
    "source_url": "https://github.com/89jobrien/steve/tree/main/steve/skills/mcp-integration",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "f739b40c52a5aac5c661a624f9d023bd2127b4abda4c5abc8ca42eaeb513871b",
    "tree_hash": "5cfc81c921f05ae3fa8bf3e5a05468ac296007b18f8f35291987c1bd119806a5",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "mcp-integration",
    "description": "Helps design, configure, review, and optimize Model Context Protocol integrations for services, APIs, databases, and developer tools.",
    "summary": "Guides MCP server configuration, authentication planning, integration design, and performance review.",
    "icon": "📦",
    "version": "1.0.2",
    "author": "Joseph OBrien",
    "license": "MIT",
    "category": "devops",
    "tags": [
      "mcp",
      "model-context-protocol",
      "integration",
      "developer-tools",
      "automation"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network",
      "env_access"
    ]
  },
  "security_audit": {
    "risk_level": "high",
    "is_blocked": false,
    "safe_to_publish": false,
    "analysis_status": "ok",
    "summary": "Most static shell-execution findings are false positives caused by Markdown code fences, not executable Ruby or shell backticks. The remaining concerns are real configuration risks: unpinned npx package execution examples and token-style credential placeholders in MCP environment blocks.",
    "remediation": [
      {
        "issue": "Unpinned npx package execution in MCP examples",
        "suggestion": "Pin package versions, verify package publishers, and require user confirmation before running generated MCP install commands.",
        "severity": "high"
      },
      {
        "issue": "Credential placeholders appear inside generated environment configuration examples",
        "suggestion": "Show references to environment variables or secret managers instead of token-shaped values or raw API key placeholders.",
        "severity": "high"
      },
      {
        "issue": "MCP command examples lack explicit safety checks",
        "suggestion": "Add guidance to review command source, package permissions, and required token scopes before enabling an MCP server.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 40,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 44
          },
          {
            "file": "SKILL.md",
            "line_start": 44,
            "line_end": 46
          },
          {
            "file": "SKILL.md",
            "line_start": 46,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 52
          },
          {
            "file": "SKILL.md",
            "line_start": 52,
            "line_end": 58
          },
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 70
          },
          {
            "file": "SKILL.md",
            "line_start": 70,
            "line_end": 96
          },
          {
            "file": "SKILL.md",
            "line_start": 96,
            "line_end": 100
          },
          {
            "file": "SKILL.md",
            "line_start": 100,
            "line_end": 113
          },
          {
            "file": "SKILL.md",
            "line_start": 113,
            "line_end": 117
          },
          {
            "file": "SKILL.md",
            "line_start": 117,
            "line_end": 119
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 108,
            "line_end": 108
          }
        ]
      },
      {
        "factor": "env_access",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 107,
            "line_end": 107
          },
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 65
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 40,
        "line_end": 42,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 44,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:44:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 44,
        "line_end": 46,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 46,
        "line_end": 50,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 52,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 52,
        "line_end": 58,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 58,
        "line_end": 70,
        "snippet": "```json"
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 70,
        "line_end": 96,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 96,
        "line_end": 100,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:100:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 100,
        "line_end": 113,
        "snippet": "```json"
      },
      {
        "id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 113,
        "line_end": 117,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 117,
        "line_end": 119,
        "snippet": "Install with: `npx claude-code-templates@latest --mcp=\"github-integration\"`"
      },
      {
        "id": "network:SKILL.md:108:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 108,
        "line_end": 108,
        "snippet": "\"GITHUB_API_URL\": \"https://api.github.com\""
      },
      {
        "id": "env_access:SKILL.md:107:git-platform-tokens",
        "category": "env_access",
        "severity": "high",
        "pattern": "Git platform tokens",
        "file": "SKILL.md",
        "line_start": 107,
        "line_end": 107,
        "snippet": "\"GITHUB_TOKEN\": \"ghp_your_token_here\","
      },
      {
        "id": "env_access:SKILL.md:65:generic-api-secret-keys",
        "category": "env_access",
        "severity": "high",
        "pattern": "Generic API/secret keys",
        "file": "SKILL.md",
        "line_start": 65,
        "line_end": 65,
        "snippet": "\"API_KEY\": \"required-env-var\""
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The detected text is a Markdown code fence around an example prompt. It is not Ruby or shell backtick execution and does not run a command."
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The finding points to a Markdown fence delimiter after an example prompt. No executable shell or Ruby code is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:44:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The detected backticks are Markdown formatting for an example request. They do not invoke a shell or evaluate Ruby code."
      },
      {
        "id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This is the closing Markdown fence for a prompt example. There is no command execution behavior in the skill file at this location."
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The finding is a Markdown code block marker around a natural-language task. It is not a shell execution primitive."
      },
      {
        "id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The line range contains Markdown structure, not executable script syntax. Any MCP command risk in later examples is handled separately."
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The detected token is a JSON code fence, not Ruby backtick execution. The embedded unpinned npx package guidance is captured as a separate semantic finding."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is Markdown formatting that closes the JSON example. It does not itself execute commands or evaluate user-controlled input."
      },
      {
        "id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The detected backticks begin a Markdown example output block. The marker is formatting, not executable shell or Ruby syntax."
      },
      {
        "id": "external_commands:SKILL.md:100:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The finding identifies a nested JSON code fence. The actual concern is the example's unpinned npx package use, which is recorded as a semantic finding."
      },
      {
        "id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The line range contains Markdown fence closure and surrounding prose. The backticks do not cause code execution."
      },
      {
        "id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "reason": "The line gives an actionable npx install command using a latest-tag package path. It is not Ruby backtick execution, but following it can run unpinned third-party code.",
        "severity": "medium"
      },
      {
        "id": "network:SKILL.md:108:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.9,
        "reason": "The URL is the standard GitHub API endpoint in a GitHub MCP example. No suspicious destination, exfiltration behavior, or hidden network request is shown."
      },
      {
        "id": "env_access:SKILL.md:107:git-platform-tokens",
        "verdict": "confirmed",
        "confidence": 0.66,
        "reason": "The example places a GitHub token-shaped value directly in an MCP environment block. It is a placeholder, but it encourages generated configs that embed high-value credentials.",
        "severity": "high"
      },
      {
        "id": "env_access:SKILL.md:65:generic-api-secret-keys",
        "verdict": "confirmed",
        "confidence": 0.56,
        "reason": "The template shows an API key field as a literal value inside an MCP configuration. No real secret is leaked, but the pattern can lead users to store secrets in generated files.",
        "severity": "high"
      }
    ],
    "semantic_findings": [
      {
        "title": "Unpinned MCP Package Execution",
        "description": "The skill examples use npx with package-name@latest and github-mcp@latest for MCP server commands. This can execute newly published package code without version pinning or publisher verification.",
        "severity": "high",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 62,
            "line_end": 63
          },
          {
            "file": "SKILL.md",
            "line_start": 104,
            "line_end": 105
          }
        ],
        "confidence": 0.93,
        "confidence_reasoning": "The command and args fields directly configure npx package execution with latest tags. This is a clear supply-chain risk if copied into an active MCP setup."
      }
    ],
    "critical_findings": [],
    "high_findings": [
      {
        "title": "Git platform tokens",
        "description": "\"GITHUB_TOKEN\": \"ghp_your_token_here\",",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 107,
            "line_end": 107
          }
        ],
        "review_kind": "capability",
        "source_category": "env_access",
        "source_severity": "high",
        "confidence": 0.66,
        "confidence_reasoning": "The example places a GitHub token-shaped value directly in an MCP environment block. It is a placeholder, but it encourages generated configs that embed high-value credentials."
      },
      {
        "title": "Generic API/secret keys",
        "description": "\"API_KEY\": \"required-env-var\"",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 65
          }
        ],
        "review_kind": "capability",
        "source_category": "env_access",
        "source_severity": "high",
        "confidence": 0.56,
        "confidence_reasoning": "The template shows an API key field as a literal value inside an MCP configuration. No real secret is leaked, but the pattern can lead users to store secrets in generated files."
      },
      {
        "title": "Unpinned MCP Package Execution",
        "description": "The skill examples use npx with package-name@latest and github-mcp@latest for MCP server commands. This can execute newly published package code without version pinning or publisher verification.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 62,
            "line_end": 63
          },
          {
            "file": "SKILL.md",
            "line_start": 104,
            "line_end": 105
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "high",
        "confidence": 0.93,
        "confidence_reasoning": "The command and args fields directly configure npx package execution with latest tags. This is a clear supply-chain risk if copied into an active MCP setup."
      }
    ],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "Install with: `npx claude-code-templates@latest --mcp=\"github-integration\"`",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 117,
            "line_end": 119
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "The line gives an actionable npx install command using a latest-tag package path. It is not Ruby backtick execution, but following it can run unpinned third-party code."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 138,
    "audit_model": "codex",
    "audited_at": "2026-07-05T12:52:07.682Z",
    "agent_auto_install_policy": "confirmation_required",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Build MCP Integrations Safely",
    "value_statement": "MCP setup can be hard to structure and secure. This skill guides Claude, Codex, and Claude Code through MCP configurations, authentication patterns, testing, and performance review.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "MCP integration",
      "Model Context Protocol",
      "MCP server configuration",
      "MCP authentication",
      "MCP performance",
      "GitHub MCP",
      "AI developer tools"
    ],
    "actual_capabilities": [
      "Drafts MCP server configuration patterns for APIs, databases, cloud services, and developer tools.",
      "Explains authentication requirements and required environment variables for MCP services.",
      "Suggests performance improvements such as connection pooling, retries, and error handling.",
      "Provides MCP integration examples for GitHub-style API connectors.",
      "Lists testing and validation checks for MCP server configurations."
    ],
    "limitations": [
      "It is documentation only and does not include executable implementation code.",
      "Examples use placeholder package names and tokens that require security review before use.",
      "It does not verify package provenance, package versions, or server compatibility.",
      "It does not test generated MCP configurations automatically."
    ],
    "use_cases": [
      {
        "title": "Create a Service MCP",
        "description": "Plan a new MCP server configuration for an API, database, or cloud service integration.",
        "target_user": "Application developer"
      },
      {
        "title": "Standardize MCP Configuration",
        "description": "Define consistent server naming, command structure, environment variables, and validation steps.",
        "target_user": "DevOps engineer"
      },
      {
        "title": "Review MCP Security",
        "description": "Check authentication, token handling, command safety, and permission boundaries before rollout.",
        "target_user": "Security reviewer"
      }
    ],
    "prompt_templates": [
      {
        "title": "Create Basic MCP Configuration",
        "scenario": "Beginner setup for a known service.",
        "prompt": "Create a basic MCP server plan for [service]. Include the server name, required environment variables, setup steps, and validation checks."
      },
      {
        "title": "Add Authentication Guidance",
        "scenario": "Intermediate setup that needs secure credentials.",
        "prompt": "Design MCP authentication for [service]. Identify required token scopes, safe secret storage, rotation steps, and failure handling."
      },
      {
        "title": "Optimize MCP Performance",
        "scenario": "Advanced review of an existing integration.",
        "prompt": "Review this MCP integration for performance. Suggest improvements for connection reuse, retries, rate limits, logging, and response validation."
      },
      {
        "title": "Audit MCP Rollout Plan",
        "scenario": "Advanced security and operations review.",
        "prompt": "Audit this MCP rollout plan. Flag command execution risk, package trust issues, credential handling gaps, and missing test coverage."
      }
    ],
    "output_examples": [
      {
        "input": "Create a GitHub MCP integration.",
        "output": "A concise plan with server purpose, package selection notes, required token scopes, endpoint details, install cautions, and validation steps."
      },
      {
        "input": "Optimize this MCP server for performance.",
        "output": "A review covering connection reuse, retry limits, response validation, logging, rate limits, and load testing."
      },
      {
        "input": "Review MCP authentication for a database connector.",
        "output": "A risk review that identifies secret storage issues, least-privilege access, rotation steps, and confirmation points."
      }
    ],
    "best_practices": [
      "Pin MCP package versions and verify publisher trust before adding commands to configurations.",
      "Use environment variables or secret managers instead of storing token values in shared files.",
      "Test each MCP server in a limited environment before granting broad repository or cloud access."
    ],
    "anti_patterns": [
      "Installing MCP packages with latest tags in unattended workflows.",
      "Embedding personal access tokens directly in generated configuration files.",
      "Granting broad API scopes before the integration has a clear access model."
    ],
    "faq": [
      {
        "question": "What does this skill help create?",
        "answer": "It helps create MCP integration plans, configuration patterns, authentication guidance, and performance review checklists."
      },
      {
        "question": "Does this skill run MCP servers?",
        "answer": "No. It provides guidance and examples, but it does not execute commands or test servers by itself."
      },
      {
        "question": "Can I use it with Claude Code and Codex?",
        "answer": "Yes. The report lists support for Claude, Codex, and Claude Code."
      },
      {
        "question": "What should I review before using generated commands?",
        "answer": "Review package source, version pinning, publisher trust, token scopes, and local execution permissions."
      },
      {
        "question": "How should secrets be handled?",
        "answer": "Use environment variables or a secret manager. Avoid placing raw token values in shared configuration files."
      },
      {
        "question": "Is this skill best for new or existing MCP projects?",
        "answer": "It can support both. Use it to plan new integrations or review existing configurations for security and performance."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 138
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall