wet-mcp

v3.15.7

Open-source MCP server for AI agents: web search, content extraction, and library docs.

Claude Code6 Skills1 MCP serverstdio

By n24q02mLicense: Apache-2.018 GitHub starsUpdated 3 days ago

Directory evidence

Runtimes: Claude Code
Parsed components: 7 skill or MCP entries
Source updated: Sep 21, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install wet-mcp for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install wet-mcp@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/n24q02m/wet

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

wet-mcp/

├── .claude-plugin/plugin.json
├── skills/compare/SKILL.md
├── skills/fact-check/SKILL.md
├── skills/lock-project-stack/SKILL.md
├── skills/research-topic/SKILL.md
├── skills/scrape-batch/SKILL.md
├── skills/wet/SKILL.md
└── .mcp.json

Included Skills6

compareskills/compare/SKILL.md

Structured comparison of 2+ alternatives with consistent criteria and decision matrix

fact-checkskills/fact-check/SKILL.md

Verify a claim using adversarial search — find both supporting AND contradicting evidence

lock-project-stackskills/lock-project-stack/SKILL.md

Detect a project's manifest (pyproject.toml / package.json / go.mod / Cargo.toml), pin its library set into wet-mcp's Cabinets project_context, then route subsequent docs queries to the locked versions automatically.

research-topicskills/research-topic/SKILL.md

Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches. Calls extract(action="agent") which searches the web, extracts top results, then synthesises a citation-preserving Markdown answer with one configured LLM.

scrape-batchskills/scrape-batch/SKILL.md

Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results plus a per-URL error list.

wetskills/wet/SKILL.md

Dùng wet CLI để tải/đọc/nén tài liệu web & library docs (web scraping, library-docs, crawl4ai, searxng). Dùng khi cần fetch docs, warmup cache, doctor kiểm tra cấu hình — thay vì mở MCP server.

MCP servers1

wetstdio

command: uvx
args: --python 3.13 wet-mcp
env.MCP_TRANSPORT: stdio
env.EMBEDDING_MODELS: ${user_config.EMBEDDING_MODELS}
env.RERANK_MODELS: ${user_config.RERANK_MODELS}
env.LLM_MODELS: ${user_config.LLM_MODELS}
env.EMBEDDING_API_BASE: ${user_config.EMBEDDING_API_BASE}
env.RERANK_API_BASE: ${user_config.RERANK_API_BASE}
env.LLM_API_BASE: ${user_config.LLM_API_BASE}
env.JINA_AI_API_KEY: ${user_config.JINA_AI_API_KEY}
env.GEMINI_API_KEY: ${user_config.GEMINI_API_KEY}
env.OPENAI_API_KEY: ${user_config.OPENAI_API_KEY}
env.OPENROUTER_API_KEY: ${user_config.OPENROUTER_API_KEY}
env.COHERE_API_KEY: ${user_config.COHERE_API_KEY}
env.GITHUB_TOKEN: ${user_config.GITHUB_TOKEN}

Plugin manifests1

.claude-plugin/plugin.json

{
  "name": "wet-mcp",
  "description": "Open-source MCP server for AI agents: web search, content extraction, and library docs.",
  "version": "3.15.7",
  "userConfig": {
    "EMBEDDING_MODELS": {
      "type": "string",
      "title": "Embedding model chain (optional)",
      "description": "CSV 'provider/model,provider/model' (order = litellm fallback); provider inferred from prefix. Empty = local ONNX through fastretrieval. Managed route: cohere/embed-v4.0 via EMBEDDING_API_BASE; paid provider use needs an approved cap.",
      "required": false
    },
    "RERANK_MODELS": {
      "type": "string",
      "title": "Rerank model chain (optional)",
      "description": "CSV 'provider/model,...'; provider inferred from prefix. Empty = local ONNX cross-encoder. Managed route: cohere/rerank-v4.0-fast via RERANK_API_BASE; paid provider use needs an approved cap.",
      "required": false
    },
    "LLM_MODELS": {
      "type": "string",
      "title": "LLM model chain (optional)",
      "description": "CSV 'provider/model,...'; provider inferred from prefix. Empty = LLM features off. Managed completion: openrouter/minimax/minimax-m3:free only, with no paid fallback.",
      "required": false
    },
    "EMBEDDING_API_BASE": {
      "type": "string",
      "title": "Embedding endpoint (optional)",
      "description": "Custom endpoint or CF AI Gateway. Cohere: <gateway>/cohere/v2/embed.",
      "required": false
    },
    "RERANK_API_BASE": {
      "type": "string",
      "title": "Rerank endpoint (optional)",
      "description": "Custom endpoint or CF AI Gateway. Cohere: <gateway>/cohere; the client appends /v1/rerank.",
      "required": false
    },
    "LLM_API_BASE": {
      "type": "string",
      "title": "Completion endpoint (optional)",
      "description": "Custom endpoint or CF AI Gateway for the selected completion model.",
      "required": false
    },
    "JINA_AI_API_KEY": {
      "type": "string",
      "title": "Jina AI API key (optional)",
      "description": "Enables jina_ai/ models referenced in a model chain. Without any cloud key the server uses local ONNX. https://jina.ai/api-dashboard/",
      "sensitive": true,
      "required": false
    },
    "GEMINI_API_KEY": {
      "type": "string",
      "title": "Gemini API key (optional)",
      "description": "Enables gemini/ models referenced in a model chain. https://ai.google.dev/",
      "sensitive": true,
      "required": false
    },
    "OPENAI_API_KEY": {
      "type": "string",
      "title": "OpenAI API key (optional)",
      "description": "Enables openai/ models referenced in a model chain. https://platform.openai.com/api-keys",
      "sensitive": true,
      "required": false
    },
    "OPENROUTER_API_KEY": {
      "type": "string",
      "title": "OpenRouter API key (optional)",
      "description": "Enables openrouter/ models in the selected chain. https://openrouter.ai/settings/keys",
      "sensitive": true,
      "required": false
    },
    "COHERE_API_KEY": {
      "type": "string",
      "title": "Cohere API key (optional)",
      "description": "Enables cohere/ models referenced in a model chain. https://dashboard.cohere.com/api-keys",
      "sensitive": true,
      "required": false
    },
    "GITHUB_TOKEN": {
      "type": "string",
      "title": "GitHub personal access token (optional)",
      "description": "Optional. Bumps GitHub API rate limit (60->5000 req/hr) for library docs discovery. https://github.com/settings/tokens",
      "sensitive": true,
      "required": false
    }
  },
  "author": {
    "name": "n24q02m",
    "url": "https://github.com/n24q02m"
  },
  "homepage": "https://github.com/n24q02m/wet",
  "repository": "https://github.com/n24q02m/wet",
  "license": "Apache-2.0",
  "keywords": [
    "web-search",
    "content-extraction",
    "documentation",
    "mcp",
    "claude-code"
  ],
  "mcpServers": {
    "wet": {
      "command": "uvx",
      "args": [
        "--python",
        "3.13",
        "wet-mcp"
      ],
      "env": {
        "MCP_TRANSPORT": "stdio",
        "EMBEDDING_MODELS": "${user_config.EMBEDDING_MODELS}",
        "RERANK_MODELS": "${user_config.RERANK_MODELS}",
        "LLM_MODELS": "${user_config.LLM_MODELS}",
        "EMBEDDING_API_BASE": "${user_config.EMBEDDING_API_BASE}",
        "RERANK_API_BASE": "${user_config.RERANK_API_BASE}",
        "LLM_API_BASE": "${user_config.LLM_API_BASE}",
        "JINA_AI_API_KEY": "${user_config.JINA_AI_API_KEY}",
        "GEMINI_API_KEY": "${user_config.GEMINI_API_KEY}",
        "OPENAI_API_KEY": "${user_config.OPENAI_API_KEY}",
        "OPENROUTER_API_KEY": "${user_config.OPENROUTER_API_KEY}",
        "COHERE_API_KEY": "${user_config.COHERE_API_KEY}",
        "GITHUB_TOKEN": "${user_config.GITHUB_TOKEN}"
      }
    }
  }
}