{
  "schemaVersion": "1.0",
  "item": {
    "slug": "mcp-client",
    "name": "Mcp Client",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/nantes/mcp-client",
    "canonicalUrl": "https://clawhub.ai/nantes/mcp-client",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/mcp-client",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mcp-client",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "mcp_client.py",
      "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",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/mcp-client"
    },
    "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/mcp-client",
    "agentPageUrl": "https://openagent3.xyz/skills/mcp-client/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mcp-client/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mcp-client/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": "MCP Client Skill",
        "body": "Implementation of the Model Context Protocol (MCP) client for connecting to tools and data sources."
      },
      {
        "title": "What it does",
        "body": "Connect to MCP Servers - Access tools and resources from MCP-enabled services\nTool Invocation - Call tools exposed by MCP servers\nResource Access - Read files, databases, APIs\nPrompt Templates - Use structured prompts from MCP servers"
      },
      {
        "title": "Installation",
        "body": "# Install Python dependencies (requests is the only required dependency)\npip install requests"
      },
      {
        "title": "Connect to MCP Server",
        "body": ".\\mcp.ps1 -Action connect -ServerUrl \"https://mcp-server.com\" -ApiKey \"your-key\""
      },
      {
        "title": "List Available Tools",
        "body": ".\\mcp.ps1 -Action tools -ServerUrl \"https://mcp-server.com\""
      },
      {
        "title": "Call a Tool",
        "body": ".\\mcp.ps1 -Action call -ServerUrl \"https://mcp-server.com\" -ToolName \"search\" -Arguments '{\"query\": \"AI agents\"}'"
      },
      {
        "title": "List Resources",
        "body": ".\\mcp.ps1 -Action resources -ServerUrl \"https://mcp-server.com\""
      },
      {
        "title": "Read a Resource",
        "body": ".\\mcp.ps1 -Action read -ServerUrl \"https://mcp-server.com\" -ResourceUri \"file:///data/config.json\""
      },
      {
        "title": "MCP Concepts",
        "body": "MCP Server: Service that exposes tools, resources, and prompts\nTools: Functions the LLM/agent can call\nResources: Data sources (files, APIs, DBs)\nPrompts: Pre-defined prompt templates"
      },
      {
        "title": "API Reference",
        "body": "POST /mcp/connect     - Connect to server\nGET  /mcp/tools       - List available tools\nPOST /mcp/call       - Invoke a tool\nGET  /mcp/resources  - List resources\nGET  /mcp/read       - Read resource\nGET  /mcp/prompts    - List prompt templates"
      },
      {
        "title": "Python Usage",
        "body": "from mcp_client import MCPClient\n\nclient = MCPClient(\"https://mcp-server.com\", api_key=\"key\")\n\n# List tools\ntools = client.list_tools()\nprint(tools)\n\n# Call tool\nresult = client.call_tool(\"search\", {\"query\": \"quantum\"})\nprint(result)\n\n# Read resource\ndata = client.read_resource(\"file:///config.json\")\nprint(data)"
      },
      {
        "title": "file:// URI Risk",
        "body": "The MCP protocol allows file:///path URIs to read files from the server. Only connect to trusted MCP servers. A malicious server could exfiltrate sensitive files."
      },
      {
        "title": "Best Practices",
        "body": "Only use MCP servers you control or trust\nDon't connect to random public MCP servers\nReview what tools/resources are available before using"
      },
      {
        "title": "Requirements",
        "body": "Review what tools/resources are available before using\n\n\nPython 3.8+\n\n\nrequests library"
      },
      {
        "title": "License",
        "body": "MIT"
      }
    ],
    "body": "MCP Client Skill\n\nImplementation of the Model Context Protocol (MCP) client for connecting to tools and data sources.\n\nWhat it does\nConnect to MCP Servers - Access tools and resources from MCP-enabled services\nTool Invocation - Call tools exposed by MCP servers\nResource Access - Read files, databases, APIs\nPrompt Templates - Use structured prompts from MCP servers\nInstallation\n# Install Python dependencies (requests is the only required dependency)\npip install requests\n\nUsage\nConnect to MCP Server\n.\\mcp.ps1 -Action connect -ServerUrl \"https://mcp-server.com\" -ApiKey \"your-key\"\n\nList Available Tools\n.\\mcp.ps1 -Action tools -ServerUrl \"https://mcp-server.com\"\n\nCall a Tool\n.\\mcp.ps1 -Action call -ServerUrl \"https://mcp-server.com\" -ToolName \"search\" -Arguments '{\"query\": \"AI agents\"}'\n\nList Resources\n.\\mcp.ps1 -Action resources -ServerUrl \"https://mcp-server.com\"\n\nRead a Resource\n.\\mcp.ps1 -Action read -ServerUrl \"https://mcp-server.com\" -ResourceUri \"file:///data/config.json\"\n\nMCP Concepts\nMCP Server: Service that exposes tools, resources, and prompts\nTools: Functions the LLM/agent can call\nResources: Data sources (files, APIs, DBs)\nPrompts: Pre-defined prompt templates\nAPI Reference\nPOST /mcp/connect     - Connect to server\nGET  /mcp/tools       - List available tools\nPOST /mcp/call       - Invoke a tool\nGET  /mcp/resources  - List resources\nGET  /mcp/read       - Read resource\nGET  /mcp/prompts    - List prompt templates\n\nExamples\nPython Usage\nfrom mcp_client import MCPClient\n\nclient = MCPClient(\"https://mcp-server.com\", api_key=\"key\")\n\n# List tools\ntools = client.list_tools()\nprint(tools)\n\n# Call tool\nresult = client.call_tool(\"search\", {\"query\": \"quantum\"})\nprint(result)\n\n# Read resource\ndata = client.read_resource(\"file:///config.json\")\nprint(data)\n\n⚠️ Security Warnings\nfile:// URI Risk\n\nThe MCP protocol allows file:///path URIs to read files from the server. Only connect to trusted MCP servers. A malicious server could exfiltrate sensitive files.\n\nBest Practices\nOnly use MCP servers you control or trust\nDon't connect to random public MCP servers\nReview what tools/resources are available before using\nRequirements\n\nReview what tools/resources are available before using\n\nPython 3.8+\n\nrequests library\n\nLicense\n\nMIT"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/nantes/mcp-client",
    "publisherUrl": "https://clawhub.ai/nantes/mcp-client",
    "owner": "nantes",
    "version": "1.0.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/mcp-client",
    "downloadUrl": "https://openagent3.xyz/downloads/mcp-client",
    "agentUrl": "https://openagent3.xyz/skills/mcp-client/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mcp-client/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mcp-client/agent.md"
  }
}