{
  "schemaVersion": "1.0",
  "item": {
    "slug": "github-mcp",
    "name": "GitHub MCP Server",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/BuddhaSource/github-mcp",
    "canonicalUrl": "https://clawhub.ai/BuddhaSource/github-mcp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/github-mcp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=github-mcp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "github-mcp",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T18:12:03.570Z",
      "expiresAt": "2026-05-10T18:12:03.570Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=github-mcp",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=github-mcp",
        "contentDisposition": "attachment; filename=\"github-mcp-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "github-mcp"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/github-mcp"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/github-mcp",
    "agentPageUrl": "https://openagent3.xyz/skills/github-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/github-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/github-mcp/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "GitHub MCP Server",
        "body": "Complete GitHub Integration for AI Agents\n\nConnect AI agents to GitHub for repository management, code operations, issue tracking, pull requests, and the full GitHub API."
      },
      {
        "title": "🤖 Agent-Native GitHub Workflows",
        "body": "Enable agents to perform complex GitHub operations that previously required manual API integration:\n\nClone and navigate repositories\nRead and modify files\nCreate issues and pull requests\nReview code and discussions\nManage branches and releases"
      },
      {
        "title": "🔐 Secure Authentication",
        "body": "OAuth-based authentication with fine-grained permissions. Agents access only what you authorize."
      },
      {
        "title": "📦 Zero Setup for Common Operations",
        "body": "Pre-configured tools for the most common GitHub workflows. No manual API calls required."
      },
      {
        "title": "Option 1: Official MCP Server (Archived - Community Maintained)",
        "body": "# Community-maintained GitHub MCP server\nnpm install -g @modelcontextprotocol/server-github\n\n# Or build from source\ngit clone https://github.com/modelcontextprotocol/servers-archived\ncd servers-archived/src/github\nnpm install\nnpm run build"
      },
      {
        "title": "Option 2: Third-Party Implementations",
        "body": "Several community implementations available. Check the MCP Registry for current options."
      },
      {
        "title": "Configuration",
        "body": "Add to your MCP client config:\n\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol/server-github\"],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"ghp_your_token_here\"\n      }\n    }\n  }\n}"
      },
      {
        "title": "Get GitHub Token",
        "body": "Go to https://github.com/settings/tokens\nGenerate new token (classic) or fine-grained token\nSelect scopes:\n\nrepo - Full repository access\nread:user - Read user profile\nread:org - Read organization data (if needed)\n\nFine-Grained Token (recommended):\n\nRepository permissions: Contents (Read/Write), Issues (Read/Write), Pull Requests (Read/Write)\nOrganization permissions: Members (Read) if accessing org repos"
      },
      {
        "title": "Repository Operations",
        "body": "1. Create Repository\n\nAgent: \"Create a new repository called 'my-project'\"\n\n2. Clone Repository\n\nAgent: \"Clone the OpenAI GPT-4 repository\"\n\n3. List Repository Files\n\nAgent: \"What files are in the src/ directory?\""
      },
      {
        "title": "File Operations",
        "body": "4. Read File\n\nAgent: \"Show me the README.md file\"\nAgent: \"Read the contents of src/index.ts\"\n\n5. Create/Update File\n\nAgent: \"Create a new file docs/API.md with API documentation\"\nAgent: \"Update the version in package.json to 2.0.0\"\n\n6. Search Code\n\nAgent: \"Search for files containing 'authentication logic'\"\nAgent: \"Find where the DatabaseConnection class is defined\""
      },
      {
        "title": "Issue & PR Management",
        "body": "7. Create Issue\n\nAgent: \"Create an issue: 'Add dark mode support'\"\n\n8. List Issues\n\nAgent: \"Show me all open bugs\"\nAgent: \"What issues are assigned to me?\"\n\n9. Create Pull Request\n\nAgent: \"Create a PR to merge feature/login into main\"\n\n10. Review Pull Request\n\nAgent: \"Review PR #42 and check for security issues\""
      },
      {
        "title": "Branch Operations",
        "body": "11. Create Branch\n\nAgent: \"Create a new branch called 'feature/user-auth'\"\n\n12. List Branches\n\nAgent: \"Show all branches in this repo\"\n\n13. Merge Branch\n\nAgent: \"Merge 'develop' into 'main'\""
      },
      {
        "title": "Advanced Operations",
        "body": "14. Create Release\n\nAgent: \"Create a release v2.0.0 with the latest changes\"\n\n15. Search Repositories\n\nAgent: \"Find popular React component libraries\"\n\n16. Fork Repository\n\nAgent: \"Fork the Vue.js repository to my account\""
      },
      {
        "title": "Code Review Automation",
        "body": "Human: \"Review all PRs and flag security issues\"\n\nAgent:\n1. list_pull_requests(state=\"open\")\n2. For each PR:\n   - get_pull_request(pr_number)\n   - read_changed_files()\n   - analyze for security vulnerabilities\n   - create_review_comment(security_findings)"
      },
      {
        "title": "Issue Triage",
        "body": "Human: \"Label all new issues with 'needs-triage'\"\n\nAgent:\n1. list_issues(state=\"open\", labels=null)\n2. For each unlabeled issue:\n   - read_issue(issue_number)\n   - add_label(\"needs-triage\")"
      },
      {
        "title": "Release Automation",
        "body": "Human: \"Prepare v2.0.0 release\"\n\nAgent:\n1. create_branch(\"release/v2.0.0\")\n2. update_file(\"package.json\", version=\"2.0.0\")\n3. update_file(\"CHANGELOG.md\", new_release_notes)\n4. create_pull_request(\"release/v2.0.0\" -> \"main\")\n5. create_release(tag=\"v2.0.0\", notes=changelog)"
      },
      {
        "title": "Documentation Sync",
        "body": "Human: \"Update documentation from code comments\"\n\nAgent:\n1. search_code(query=\"* @description\")\n2. extract_docstrings()\n3. generate_markdown_docs()\n4. update_file(\"docs/API.md\", generated_docs)\n5. create_pull_request(\"Update API documentation\")"
      },
      {
        "title": "🛠️ Development Assistants",
        "body": "Agents that help developers with repetitive GitHub tasks: creating issues, managing labels, updating documentation, code review."
      },
      {
        "title": "🤖 CI/CD Automation",
        "body": "Build agents that trigger workflows, check build status, create releases, manage deployments."
      },
      {
        "title": "📊 Repository Analytics",
        "body": "Analyze code quality, track issue resolution time, monitor PR velocity, generate reports."
      },
      {
        "title": "🔍 Code Search & Discovery",
        "body": "Find code patterns, identify dependencies, discover similar implementations, locate technical debt."
      },
      {
        "title": "📝 Documentation Automation",
        "body": "Sync code comments to docs, generate API references, update changelogs, maintain README files."
      },
      {
        "title": "✅ Use Fine-Grained Tokens",
        "body": "Prefer fine-grained tokens over classic PATs. Limit scope to specific repositories and permissions."
      },
      {
        "title": "✅ Read-Only When Possible",
        "body": "If the agent only needs to read code/issues, grant read-only access."
      },
      {
        "title": "✅ Environment Variables",
        "body": "Never hard-code tokens. Always use environment variables."
      },
      {
        "title": "✅ Token Rotation",
        "body": "Rotate tokens regularly. Set expiration dates."
      },
      {
        "title": "✅ Audit Agent Actions",
        "body": "Monitor what the agent does. GitHub activity log tracks all API operations."
      },
      {
        "title": "Rate Limits",
        "body": "Authenticated Requests:\n\n5,000 requests/hour (per user)\nSearch API: 30 requests/minute\n\nBest Practices:\n\nCache repository data when possible\nBatch operations where applicable\nUse conditional requests (If-None-Match headers)"
      },
      {
        "title": "vs Manual GitHub API Integration",
        "body": "TaskManual APIGitHub MCPSetup TimeHours (auth, SDK, error handling)Minutes (config file)Code RequiredYes (HTTP client, auth, parsing)No (MCP tools auto-discovered)Agent IntegrationManual tool definitionsAutomatic via MCPAuth ManagementCustom implementationBuilt-in OAuth flowError HandlingCustom retry logicHandled by server"
      },
      {
        "title": "\"Bad credentials\" Error",
        "body": "Verify token has not expired\nEnsure token has required scopes (repo, read:user)\nCheck token is correctly set in environment variable"
      },
      {
        "title": "\"Resource not found\" Error",
        "body": "Verify repository name format: owner/repo\nCheck agent has access to private repositories (if applicable)\nEnsure branch/file path exists"
      },
      {
        "title": "Rate Limit Errors",
        "body": "Wait for rate limit reset (check X-RateLimit-Reset header)\nReduce query frequency\nConsider GitHub Apps for higher limits"
      },
      {
        "title": "Resources",
        "body": "MCP Registry: https://registry.modelcontextprotocol.io/\nGitHub API Docs: https://docs.github.com/en/rest\nCreate Token: https://github.com/settings/tokens\nRate Limits: https://docs.github.com/en/rest/overview/rate-limits-for-the-rest-api"
      },
      {
        "title": "Advanced Configuration",
        "body": "{\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"node\",\n      \"args\": [\"/path/to/github-mcp/build/index.js\"],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"ghp_xxx\",\n        \"GITHUB_API_URL\": \"https://api.github.com\",\n        \"DEFAULT_BRANCH\": \"main\",\n        \"AUTO_PAGINATION\": \"true\"\n      }\n    }\n  }\n}\n\nThe GitHub integration every coding agent needs: From code review to release automation, GitHub MCP brings the full power of GitHub to AI agents."
      }
    ],
    "body": "GitHub MCP Server\n\nComplete GitHub Integration for AI Agents\n\nConnect AI agents to GitHub for repository management, code operations, issue tracking, pull requests, and the full GitHub API.\n\nWhy GitHub MCP?\n🤖 Agent-Native GitHub Workflows\n\nEnable agents to perform complex GitHub operations that previously required manual API integration:\n\nClone and navigate repositories\nRead and modify files\nCreate issues and pull requests\nReview code and discussions\nManage branches and releases\n🔐 Secure Authentication\n\nOAuth-based authentication with fine-grained permissions. Agents access only what you authorize.\n\n📦 Zero Setup for Common Operations\n\nPre-configured tools for the most common GitHub workflows. No manual API calls required.\n\nInstallation\nOption 1: Official MCP Server (Archived - Community Maintained)\n# Community-maintained GitHub MCP server\nnpm install -g @modelcontextprotocol/server-github\n\n# Or build from source\ngit clone https://github.com/modelcontextprotocol/servers-archived\ncd servers-archived/src/github\nnpm install\nnpm run build\n\nOption 2: Third-Party Implementations\n\nSeveral community implementations available. Check the MCP Registry for current options.\n\nConfiguration\n\nAdd to your MCP client config:\n\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol/server-github\"],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"ghp_your_token_here\"\n      }\n    }\n  }\n}\n\nGet GitHub Token\nGo to https://github.com/settings/tokens\nGenerate new token (classic) or fine-grained token\nSelect scopes:\nrepo - Full repository access\nread:user - Read user profile\nread:org - Read organization data (if needed)\n\nFine-Grained Token (recommended):\n\nRepository permissions: Contents (Read/Write), Issues (Read/Write), Pull Requests (Read/Write)\nOrganization permissions: Members (Read) if accessing org repos\nAvailable Tools\nRepository Operations\n1. Create Repository\nAgent: \"Create a new repository called 'my-project'\"\n\n2. Clone Repository\nAgent: \"Clone the OpenAI GPT-4 repository\"\n\n3. List Repository Files\nAgent: \"What files are in the src/ directory?\"\n\nFile Operations\n4. Read File\nAgent: \"Show me the README.md file\"\nAgent: \"Read the contents of src/index.ts\"\n\n5. Create/Update File\nAgent: \"Create a new file docs/API.md with API documentation\"\nAgent: \"Update the version in package.json to 2.0.0\"\n\n6. Search Code\nAgent: \"Search for files containing 'authentication logic'\"\nAgent: \"Find where the DatabaseConnection class is defined\"\n\nIssue & PR Management\n7. Create Issue\nAgent: \"Create an issue: 'Add dark mode support'\"\n\n8. List Issues\nAgent: \"Show me all open bugs\"\nAgent: \"What issues are assigned to me?\"\n\n9. Create Pull Request\nAgent: \"Create a PR to merge feature/login into main\"\n\n10. Review Pull Request\nAgent: \"Review PR #42 and check for security issues\"\n\nBranch Operations\n11. Create Branch\nAgent: \"Create a new branch called 'feature/user-auth'\"\n\n12. List Branches\nAgent: \"Show all branches in this repo\"\n\n13. Merge Branch\nAgent: \"Merge 'develop' into 'main'\"\n\nAdvanced Operations\n14. Create Release\nAgent: \"Create a release v2.0.0 with the latest changes\"\n\n15. Search Repositories\nAgent: \"Find popular React component libraries\"\n\n16. Fork Repository\nAgent: \"Fork the Vue.js repository to my account\"\n\nAgent Workflow Examples\nCode Review Automation\nHuman: \"Review all PRs and flag security issues\"\n\nAgent:\n1. list_pull_requests(state=\"open\")\n2. For each PR:\n   - get_pull_request(pr_number)\n   - read_changed_files()\n   - analyze for security vulnerabilities\n   - create_review_comment(security_findings)\n\nIssue Triage\nHuman: \"Label all new issues with 'needs-triage'\"\n\nAgent:\n1. list_issues(state=\"open\", labels=null)\n2. For each unlabeled issue:\n   - read_issue(issue_number)\n   - add_label(\"needs-triage\")\n\nRelease Automation\nHuman: \"Prepare v2.0.0 release\"\n\nAgent:\n1. create_branch(\"release/v2.0.0\")\n2. update_file(\"package.json\", version=\"2.0.0\")\n3. update_file(\"CHANGELOG.md\", new_release_notes)\n4. create_pull_request(\"release/v2.0.0\" -> \"main\")\n5. create_release(tag=\"v2.0.0\", notes=changelog)\n\nDocumentation Sync\nHuman: \"Update documentation from code comments\"\n\nAgent:\n1. search_code(query=\"* @description\")\n2. extract_docstrings()\n3. generate_markdown_docs()\n4. update_file(\"docs/API.md\", generated_docs)\n5. create_pull_request(\"Update API documentation\")\n\nUse Cases\n🛠️ Development Assistants\n\nAgents that help developers with repetitive GitHub tasks: creating issues, managing labels, updating documentation, code review.\n\n🤖 CI/CD Automation\n\nBuild agents that trigger workflows, check build status, create releases, manage deployments.\n\n📊 Repository Analytics\n\nAnalyze code quality, track issue resolution time, monitor PR velocity, generate reports.\n\n🔍 Code Search & Discovery\n\nFind code patterns, identify dependencies, discover similar implementations, locate technical debt.\n\n📝 Documentation Automation\n\nSync code comments to docs, generate API references, update changelogs, maintain README files.\n\nSecurity Best Practices\n✅ Use Fine-Grained Tokens\n\nPrefer fine-grained tokens over classic PATs. Limit scope to specific repositories and permissions.\n\n✅ Read-Only When Possible\n\nIf the agent only needs to read code/issues, grant read-only access.\n\n✅ Environment Variables\n\nNever hard-code tokens. Always use environment variables.\n\n✅ Token Rotation\n\nRotate tokens regularly. Set expiration dates.\n\n✅ Audit Agent Actions\n\nMonitor what the agent does. GitHub activity log tracks all API operations.\n\nRate Limits\n\nAuthenticated Requests:\n\n5,000 requests/hour (per user)\nSearch API: 30 requests/minute\n\nBest Practices:\n\nCache repository data when possible\nBatch operations where applicable\nUse conditional requests (If-None-Match headers)\nvs Manual GitHub API Integration\nTask\tManual API\tGitHub MCP\nSetup Time\tHours (auth, SDK, error handling)\tMinutes (config file)\nCode Required\tYes (HTTP client, auth, parsing)\tNo (MCP tools auto-discovered)\nAgent Integration\tManual tool definitions\tAutomatic via MCP\nAuth Management\tCustom implementation\tBuilt-in OAuth flow\nError Handling\tCustom retry logic\tHandled by server\nTroubleshooting\n\"Bad credentials\" Error\nVerify token has not expired\nEnsure token has required scopes (repo, read:user)\nCheck token is correctly set in environment variable\n\"Resource not found\" Error\nVerify repository name format: owner/repo\nCheck agent has access to private repositories (if applicable)\nEnsure branch/file path exists\nRate Limit Errors\nWait for rate limit reset (check X-RateLimit-Reset header)\nReduce query frequency\nConsider GitHub Apps for higher limits\nResources\nMCP Registry: https://registry.modelcontextprotocol.io/\nGitHub API Docs: https://docs.github.com/en/rest\nCreate Token: https://github.com/settings/tokens\nRate Limits: https://docs.github.com/en/rest/overview/rate-limits-for-the-rest-api\nAdvanced Configuration\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"node\",\n      \"args\": [\"/path/to/github-mcp/build/index.js\"],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"ghp_xxx\",\n        \"GITHUB_API_URL\": \"https://api.github.com\",\n        \"DEFAULT_BRANCH\": \"main\",\n        \"AUTO_PAGINATION\": \"true\"\n      }\n    }\n  }\n}\n\n\nThe GitHub integration every coding agent needs: From code review to release automation, GitHub MCP brings the full power of GitHub to AI agents."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/BuddhaSource/github-mcp",
    "publisherUrl": "https://clawhub.ai/BuddhaSource/github-mcp",
    "owner": "BuddhaSource",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/github-mcp",
    "downloadUrl": "https://openagent3.xyz/downloads/github-mcp",
    "agentUrl": "https://openagent3.xyz/skills/github-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/github-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/github-mcp/agent.md"
  }
}