WET - Web Extended Toolkit MCP Server

WET - Web Extended Toolkit MCP Server

mcp-name: io.github.n24q02m/wet-mcp

Web search, content extraction, and library docs for AI agents -- 5-strategy scraping, runs without API keys.

Current release: v3.x. media(action="analyze") was removed in thev2.0.0 BREAKING release. Useimagine-mcp'sunderstand action for vision/audio/video analysis. Seedocs/migration.md for the upgrade recipe.

Table of contents

• Features
• Status
• Quick install
• Configuration
• Documentation
• Tools
• Comparison
• Security
• Build from Source
• Deploy to Cloudflare
• Trust Model
• License

Features

• Web Search -- Embedded SearXNG metasearch (Google, Bing, DuckDuckGo, Brave) with query expansion, TTL cache (1 h general / 5 min time-sensitive), standardized citation format, and 200-token snippet cap. Optional cloud search backends (Tavily, Brave, Exa) as a fallback chain via SEARCH_BACKENDS
• Academic Research -- Search Google Scholar, Semantic Scholar, arXiv, PubMed, CrossRef, BASE
• Library Docs -- Auto-discover and index documentation with FTS5 hybrid search, HyDE-enhanced retrieval, and version-specific docs
• Content Extract -- 5-strategy escalation chain via n24q02m-web-core ScrapingAgent (basic_http -> tls_spoof -> headless Crawl4AI), markitdown bridge for low-tier HTML/MD fallback, smart chunks structured output (clean text + markdown + JSON-LD + code blocks + metadata), batch processing (up to 50 URLs), deep crawling, site mapping
• Local File Conversion -- Convert PDF, DOCX, XLSX, CSV, HTML, EPUB, PPTX to Markdown
• Media -- List + download images / videos / audio files. analyze was removed in v2.0.0 -- use imagine-mcp.understand for vision/audio inference
• Anti-bot -- Stealth strategies bypass Cloudflare, Medium, LinkedIn, Twitter
• Zero Config -- Built-in local Qwen3 embedding + reranking, no API keys needed. Optional cloud providers (Jina AI, Gemini, OpenAI, Cohere, xAI, Anthropic) selected per task via the EMBEDDING_MODELS / RERANK_MODELS / LLM_MODELS model chains for higher-quality vectors and LLM features
• Sync -- Cross-machine sync of indexed docs via Google Drive (OAuth Device Code, no browser redirect)

Quick install

# Method 1 (default): plugin install via Claude Code
/plugin marketplace add n24q02m/claude-plugins
/plugin install wet-mcp@n24q02m-plugins

# Method 2 (CLI): direct uvx invocation
claude mcp add wet -- uvx wet-mcp

# Method 3 (recommended for HTTP / multi-device / OAuth)
docker run -d --name wet-mcp-http -p 8084:8080 \
  -v wet-data:/data -e MCP_TRANSPORT=http \
  -e PUBLIC_URL=https://wet.example.com \
  n24q02m/wet-mcp:latest

Full setup matrices live at the canonical docs sitemcp.n24q02m.com/servers/wet-mcp/setup/and the paste-to-agent snippets atclaude-plugins/plugins/wet-mcp/setup-with-agent.md(per Spec F single source of truth).

Configuration

wet runs zero-config out of the box: web search uses an embedded local SearXNG,and embedding/reranking fall back to the bundled local Qwen3 ONNX models when nocloud keys are set. For higher-quality results, point each task at a cloud modelchain. All settings are plain environment variables (no app prefix) -- in theHTTP self-host mode they are entered through the browser setup form instead.

Model chains (CSV provider/model,provider/model; order = fallback). Leave achain empty to use the local ONNX models (embedding/rerank) or to disable LLMfeatures (LLM):

Provider keys -- the provider is inferred from each model's prefix; supply thematching key (litellm <PROVIDER>_API_KEY convention):

Any other litellm provider works via env passthrough -- seelitellm provider docs for its key name.

Search backends -- SEARCH_BACKENDS (CSV, runtime fallback chain) oversearxng (default, local) plus optional cloud providers tavily / brave /exa. Point at an external SearXNG with SEARXNG_URL. Cloud providers needTAVILY_API_KEY / BRAVE_API_KEY / EXA_API_KEY.

Docs sync -- SYNC_ENABLED (default true), GOOGLE_DRIVE_CLIENT_ID(required for sync), SYNC_FOLDER (default wet-mcp), SYNC_INTERVAL (default300s). Sync uses Google Drive over the OAuth Device Code flow (no browserredirect).

HTTP self-host -- MCP_TRANSPORT=http, PUBLIC_URL=<your-domain>. The setupform is gated by MCP_RELAY_PASSWORD; multi-user deployments also requireCREDENTIAL_SECRET (per-user vault key) and MCP_DCR_SERVER_SECRET.

Example stdio config (cloud chains):

{
  "mcpServers": {
    "wet": {
      "command": "uvx",
      "args": ["wet-mcp"],
      "env": {
        "EMBEDDING_MODELS": "jina_ai/jina-embeddings-v5-text-small",
        "RERANK_MODELS": "jina_ai/jina-reranker-v3",
        "LLM_MODELS": "gemini/gemini-3-flash-preview",
        "JINA_AI_API_KEY": "jina_xxx",
        "GEMINI_API_KEY": "AIza_xxx"
      }
    }
  }
}

Status

Stable architecture with two transports: stdio (default, local) andHTTP (self-host, OAuth-gated). No daemon-bridge layer and no auto-spawnfrom stdio. The media.analyze action was removed in the v2.0.0 BREAKINGrelease -- see docs/migration.md for the upgraderecipe. Current release line: v3.x.

Documentation

Full docs at mcp.n24q02m.com/servers/wet-mcp/setup/:

• Setup -- install methods for Claude Code, Codex, Gemini CLI, Cursor, Windsurf, mcp.json
• Modes overview -- stdio / local-relay / remote-relay / remote-oauth
• Multi-user setup -- per-JWT-sub credential model

In-repo references (Spec F single source of truth: setup docs live inclaude-plugins/plugins/wet-mcp/):

• docs/ARCHITECTURE.md -- web-core ScrapingAgent integration, strategy chain, storage layout, LLM provider dispatch
• docs/BENCHMARKS.md -- v1.x baseline coverage / latency placeholders + tier-1 fixture metrics

Install with AI agent -- paste this to your AI coding agent:

Install MCP server wet-mcp following the steps athttps://raw.githubusercontent.com/n24q02m/claude-plugins/main/plugins/wet-mcp/setup-with-agent.md

Tools

6 MCP tools (3 domain + config + help + config__open_relay). The legacysetup tool merged into config action dispatch.

Media boundary: For vision / audio understanding (image captioning,OCR, audio transcription, video summarization), useimagine-mcp. media.analyzewas removed in wet v2.0.0 -- use imagine-mcp.understand instead.

Comparison

How wet-mcp stacks up against direct competitors in each pillar:

Security

• SSRF prevention -- URL validation on crawl targets
• Graceful fallbacks -- Cloud → Local embedding, multi-tier crawling
• Error sanitization -- No credentials in error messages
• File conversion sandboxing -- Optional CONVERT_ALLOWED_DIRS restriction

Build from Source

git clone https://github.com/n24q02m/wet-mcp.git
cd wet-mcp
uv sync
uv run wet-mcp

Deploy to Cloudflare

Run your own single-user wet instance serverless on Cloudflare (Containers + D1 + Vectorize + KV).

Prerequisites: a Cloudflare account on the Workers Paid plan and the wrangler CLI.

1. git clone https://github.com/n24q02m/wet-mcp && cd wet-mcp
2. wrangler login
3. Provision resources and apply the D1 schema:

   wrangler d1 create wet-docs
   wrangler d1 execute wet-docs --file migrations/0001_init_wet.sql --remote
   wrangler vectorize create wet-docs-vectors --dimensions 768 --metric cosine
   wrangler kv namespace create wet-kv
   

   Paste the returned IDs into wrangler.jsonc.
4. Push the container image to your Cloudflare managed registry (CF Containers cannotpull from external registries directly), then set <YOUR_ACCOUNT_ID> in wrangler.jsonc:

   docker pull ghcr.io/n24q02m/wet-mcp:beta
   docker tag ghcr.io/n24q02m/wet-mcp:beta wet-mcp:beta
   wrangler containers push wet-mcp:beta   # prints registry.cloudflare.com/<ACCOUNT_ID>/wet-mcp:beta
   

5. Set secrets (use SEARXNG_URL with basic-auth userinfo, e.g.https://user:[email protected], or TAVILY_API_KEY if you set SEARCH_BACKEND=tavily):

   wrangler secret put CREDENTIAL_SECRET
   wrangler secret put JINA_AI_API_KEY
   wrangler secret put GOOGLE_VERTEX_EXPRESS_API_KEY
   wrangler secret put XAI_API_KEY
   wrangler secret put MCP_RELAY_PASSWORD
   wrangler secret put MCP_DCR_SERVER_SECRET
   wrangler secret put SEARXNG_URL
   

6. wrangler deploy and complete setup in the browser relay form at your Worker domain.

Storage maps to Cloudflare via MCP_STORAGE_BACKEND=cf-kv (credentials/tokens, encrypted),DOCS_DB_BACKEND=cf-d1 (docs + BM25 full-text), and Vectorize (embeddings). Web search usesa SearXNG instance (SEARCH_BACKEND=searxng, SEARXNG_URL) or Tavily (SEARCH_BACKEND=tavily);embed/rerank are forced cloud via EMBEDDING_MODELS/RERANK_MODELS.

Trust Model

This plugin implements TC-Local (machine-bound, single trust principal). See mcp-core trust model for full classification.

License

MIT -- See LICENSE.