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.

Phase	Status	Scope
Phase 1	Shipped	web-core ScrapingAgent migration, smart chunks output, search polish, media slim
Phase 2	Shipped	Context7-level docs search: library index (Tier 1 + Tier 2), version-aware queries with token cap, project lock (Cabinets)
Phase 3	Shipped	extract.agent multi-step research with cited synthesis, extract.interact click/fill/submit via patchright (optional session persistence), docs_004_chunk_summaries migration, media.analyze removed (v2.0.0)

Current release: v3.x. media(action="analyze") was removed in the v2.0.0 BREAKING release. Use imagine-mcp's understand action for vision/audio/video analysis. See docs/migration.md for the upgrade recipe.

Sister projects from n24q02m (click to expand)

Project	Tagline	Tag
better-code-review-graph	Knowledge graph for token-efficient code reviews -- semantic search and call-...	MCP
better-email-mcp	IMAP/SMTP email for AI agents -- read, send, organize folders, and manage att...	MCP
better-godot-mcp	Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted g...	MCP
better-notion-mcp	Markdown-first Notion for AI agents -- pages, databases, blocks, and comments...	MCP
better-telegram-mcp	Telegram for AI agents -- messages, chats, media, and contacts across both bo...	MCP
claude-plugins	Claude Code plugin marketplace for the n24q02m MCP servers -- install web sea...	Marketplace
imagine-mcp	Image and video understanding + generation for AI agents -- across Gemini, Op...	MCP
jules-task-archiver	Chrome Extension for bulk operations on Jules tasks via batchexecute API -- a...	Tooling
mcp-core	Shared foundation for building MCP servers -- Streamable HTTP transport, OAut...	MCP
mnemo-mcp	Persistent AI memory with hybrid search and embedded sync. Open, free, unlimi...	MCP
qwen3-embed	Lightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUF	Library
skret	Secrets without the server.	CLI
tacet	TACET: a self-distilling neuro-symbolic cascade that amortises LLM cost in kn...	Tooling
web-core	Shared web infrastructure package for search, scraping, HTTP security, and st...	Library
wet-mcp	Open-source MCP server for AI agents: web search, content extraction, and lib...	MCP

Table of contents

• Features
• Status
• Quick install
• Configuration
• Documentation
• Tools
• CLI
• Comparison
• Security
• Build from Source
• Deploy to Cloudflare
• Smithery
• 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 -> render backends from BROWSER_BACKENDS (native / browserless / cf-browser-rendering) -> optional key-gated captcha), 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

# Method 4 (hosted): connect to the maintainer-run instance
claude mcp add --transport http wet https://wet.n24q02m.com/mcp

The hosted endpoint https://wet.n24q02m.com/mcp speaks Streamable HTTP and is OAuth-gated -- your client is prompted to authenticate in the browser on first connect (no API key to paste). Self-host the same HTTP mode via Method 3 or the Deploy to Cloudflare section.

Full setup matrices live at the canonical docs site mcp.n24q02m.com/servers/wet-mcp/setup/ and the paste-to-agent snippets at claude-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 no cloud keys are set. For higher-quality results, point each task at a cloud model chain. All settings are plain environment variables (no app prefix) -- in the HTTP self-host mode they are entered through the browser setup form instead.

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

Env var	Task	Empty default
EMBEDDING_MODELS	Embeddings for docs search	Local Qwen3-Embedding ONNX
RERANK_MODELS	Result reranking	Local Qwen3-Reranker ONNX
LLM_MODELS	extract(action="agent") synthesis	LLM features disabled

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

Model prefix	Key env var	Get it at
jina_ai/	JINA_AI_API_KEY	jina.ai/api-key
gemini/	GEMINI_API_KEY	aistudio.google.com/apikey
vertex_express/	GOOGLE_VERTEX_EXPRESS_API_KEY	cloud.google.com/vertex-ai/generative-ai/docs/start/express-mode/overview
openai/ (or bare)	OPENAI_API_KEY	platform.openai.com
cohere/	COHERE_API_KEY	dashboard.cohere.com
xai/	XAI_API_KEY	console.x.ai
anthropic/	ANTHROPIC_API_KEY	console.anthropic.com

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

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

Browser render backends -- BROWSER_BACKENDS (CSV, escalation chain) picks the headless render leg of extract: native (in-process chromium, the zero-config default), browserless (self-host render service -- set BROWSERLESS_URL + BROWSERLESS_TOKEN), and cf-browser-rendering (Cloudflare Browser Rendering -- set CF_ACCOUNT_ID + CF_BROWSER_RENDERING_TOKEN). Empty chain falls back to native. Set CAPSOLVER_API_KEY to append an optional, key-gated CAPTCHA tier as the last escalation step.

Disable local fallbacks -- opt out of the heavy in-process local fallbacks per capability (e.g. on a slim container that renders/searches/embeds via cloud backends only): DISABLE_LOCAL_BROWSER, DISABLE_LOCAL_SEARCH, DISABLE_LOCAL_EMBED, DISABLE_LOCAL_RERANK.

Docs sync -- SYNC_ENABLED (default true), GOOGLE_DRIVE_CLIENT_ID (required for sync), SYNC_FOLDER (default wet-mcp), SYNC_INTERVAL (default 300s). Sync uses Google Drive over the OAuth Device Code flow (no browser redirect).

HTTP self-host -- MCP_TRANSPORT=http, PUBLIC_URL=<your-domain>. The setup form is gated by MCP_RELAY_PASSWORD; multi-user deployments also require CREDENTIAL_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) and HTTP (self-host, OAuth-gated). No daemon-bridge layer and no auto-spawn from stdio. The media.analyze action was removed in the v2.0.0 BREAKING release -- see docs/migration.md for the upgrade recipe. 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 in claude-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 at https://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 legacy setup tool merged into config action dispatch.

Tool	Description
search	Web (SearXNG metasearch), news, images, academic research (Scholar / arXiv / PubMed / CrossRef / Semantic Scholar / BASE), library docs (HyDE + FTS5), find similar pages. Includes docs_resolve (library name -> ranked id), docs_query (version-aware + topic + 5000-token cap), docs_lock_project (Cabinets project pin via pyproject / package.json / go.mod / Cargo.toml manifest detection).
extract	URL -> smart chunks dict (clean_text + markdown + structured_data + code_blocks + metadata) via web-core 5-strategy chain. Batch processing (up to 50 URLs), deep crawling, site mapping, local file conversion (PDF/DOCX/XLSX/PPTX/EPUB), structured extraction (JSON Schema)
media	list (discover URLs from gallery pages), download (SSRF-safe). analyze was removed in v2.0.0 -- use imagine-mcp.understand instead
config	status, set, cache_clear, docs_reindex, warmup, setup_sync, setup_status, setup_skip, setup_reset, setup_complete
help	Per-tool documentation: search, extract, media, config
config__open_relay	Re-trigger the zero-config relay setup flow (prints a fresh relay URL for the browser form). Registered via mcp-core's register_open_relay_tool so an LLM can restart setup without a manual restart.

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

CLI

The wet-mcp console script starts the server and also exposes a few one-shot operator subcommands. A bare invocation (or any leading-dash flag) starts the server; a leading positional argument is dispatched as a subcommand.

wet-mcp                        # start the server over stdio (default transport)
wet-mcp --http                 # start the server over Streamable HTTP (self-host mode)

wet-mcp auth google            # authorize the Google credential provider for Drive sync
wet-mcp logout                 # clear the local Google Drive sync token
wet-mcp warmup                 # pre-download local models + run auto-setup (SearXNG, browser) to avoid first-run delays
wet-mcp docs reindex <library> # drop the cached docs index for <library>; the next docs search re-indexes it

auth google accepts an optional bring-your-own OAuth client via --client-id and --client-secret (single-user / local machine only; the token is written to the local store). Each subcommand prints a JSON result and exits.

Capability	wet-mcp	Brave Search	Tavily	Firecrawl	Context7
Web search	Yes (SearXNG aggregation)	Yes	Yes	No	No
Extract URL	Yes (5-strategy chain)	No	Yes (basic)	Yes	No
Media list / download	Yes	No	No	No	No
Library docs search	Yes (Tier 1 curated + Tier 2 on-demand, version-aware, Cabinets)	No	No	No	Yes
Academic research	Yes (6 providers)	No	No	No	No
Self-hostable	Yes	No	No	No	Yes
Free tier	Yes (open source)	Limited	Limited	Limited	Yes

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 — required for Containers, D1, and Vectorize (the Cloudflare free tier does not include them) — 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 cannot pull 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:pass@searxng.example.com, 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
   wrangler secret put BROWSERLESS_URL          # render backend (BROWSER_BACKENDS default = browserless,cf-browser-rendering)
   wrangler secret put BROWSERLESS_TOKEN
   wrangler secret put CF_BROWSER_RENDERING_TOKEN
   

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 uses a SearXNG instance (SEARCH_BACKEND=searxng, SEARXNG_URL) or Tavily (SEARCH_BACKEND=tavily); embed/rerank are forced cloud via EMBEDDING_MODELS/RERANK_MODELS.

Smithery

wet-mcp ships a smithery.yaml so it can be installed and run through Smithery. The manifest declares a stdio start command (uvx --python 3.13 wet-mcp) with an empty config schema -- no config is required to start, and providers and credentials are configured at runtime via the server's own config flow (see Configuration).

Trust Model

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

Mode	Storage	Encryption	Who can read your data?
stdio (default)	~/.wet-mcp/config.json	AES-GCM, machine-bound key	Only your OS user (file perm 0600)
HTTP self-host	Same as stdio	Same	Only you (admin = user)

License

MIT -- See LICENSE.