convez.ai
MCP ServerBusca & PesquisaIntermediário
n24q02m

WET - Web Extended Toolkit MCP

n24q02m/wet-mcp

Busca, extração e pesquisa web avançada para agentes Claude

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP open-source para buscas web, extração de conteúdo, documentação de bibliotecas e análise multimodal. Integra múltiplas estratégias de pesquisa, scraping inteligente e interação com páginas via browser automation (Patchright).

Instalação

$npx convez-ai n24q02m/wet-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
24
Forks
7
Acompanhando
0
Saúde
100%
Último commit
há 2 dias
Versão
v3.22.0
Issues abertas
1
Contribuidores
8

Casos de uso

  • Pesquisa web com síntese citada para agentes Claude
  • Extração de conteúdo com múltiplas estratégias de scrapling
  • Busca em documentação de bibliotecas com chunking inteligente
  • Interação com formulários e cliques em páginas web
  • Pesquisa em projetos específicos com context7-level docs

Veredito

Ferramenta madura e bem mantida (v2.0.0 com breaking changes gerenciadas). Excelente para agentes que precisam pesquisar, extrair e interagir com conteúdo web. Requer migração de código legado, mas oferece capacidades robustas de research automatizado.

README

A tradução para o português deste README ainda está na fila.

WET - Web Extended Toolkit MCP Server

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

5-strategy web search + extract + media MCP server, web-core ScrapingAgent backend.

PhaseStatusScope
Phase 1Shippedweb-core ScrapingAgent migration, smart chunks output, search polish, media slim
Phase 2ShippedContext7-level docs search: library index (Tier 1 + Tier 2), version-aware queries with token cap, project lock (Cabinets)
Phase 3Current (BREAKING v2.0.0)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

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

CI codecov PyPI Docker License: MIT

Python SearXNG MCP semantic-release Renovate

ProjectTaglineTag
better-code-review-graphKnowledge graph for token-efficient code reviews -- fixed search, configurabl...MCP
better-email-mcpIMAP/SMTP email server for AI agents -- 6 composite tools with multi-account ...MCP
better-godot-mcpComposite MCP server for Godot Engine -- 17 mega-tools for AI-assisted game d...MCP
better-notion-mcpMarkdown-first Notion API server for AI agents -- 10 composite tools replacin...MCP
better-telegram-mcpMCP server for Telegram with dual-mode support: Bot API (httpx) for quick bot...MCP
claude-pluginsFull documentation: mcp.n24q02m.com — unified docs for all 8 servers + the mc...Marketplace
imagine-mcpProduction-grade MCP server for image and video understanding + generation ac...MCP
jules-task-archiverChrome Extension for bulk operations on Jules tasks via batchexecute API -- a...Tooling
mcp-coreUnified MCP Streamable HTTP 2025-11-25 transport, OAuth 2.1 Authorization Ser...MCP
mnemo-mcpPersistent AI memory with hybrid search and embedded sync. Open, free, unlimi...MCP
qwen3-embedLightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUFLibrary
skretSecrets without the server.CLI
web-coreShared web infrastructure package for search, scraping, HTTP security, and st...Library
wet-mcpOpen-source MCP Server for web search, content extraction, library docs & mul...MCP

Table of contents

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
  • 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 deprecated v<auto>+ -- 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) for higher-quality vectors
  • 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 1 (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 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).

Status

2026-05-02 -- Architecture stabilization update

Past months saw significant churn around credential handling and the daemon-bridge auto-spawn pattern. This caused multi-process races, browser tab spam, and inconsistent setup UX across plugins. As of v<auto>, the architecture is stable: 2 clean modes (stdio + HTTP), no daemon-bridge layer, no auto-spawn from stdio.

Apologies for the instability period. If you encountered issues with prior versions, please update to v<auto>+ and follow the current setup docs -- most prior workarounds are no longer needed.

Related plugins from the same author:

All plugins share the same architecture (this spec) -- install once, learn pattern transfers.

Documentation

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

  • 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

5 MCP tools (3 domain + config + help). The legacy setup tool merged into config action dispatch.

ToolDescription
searchWeb (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).
extractURL -> 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)
medialist (discover URLs from gallery pages), download (SSRF-safe). analyze deprecated v<auto>+ -- forwards to imagine-mcp.understand
configstatus, set, cache_clear, docs_reindex, warmup, setup_sync, setup_status, setup_skip, setup_reset, setup_complete
helpPer-tool documentation: search, extract, media, config

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.

Comparison

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

Capabilitywet-mcpBrave SearchTavilyFirecrawlContext7
Web searchYes (SearXNG aggregation)YesYesNoNo
Extract URLYes (5-strategy chain)NoYes (basic)YesNo
Media list / downloadYesNoNoNoNo
Library docs searchYes (Tier 1 curated + Tier 2 on-demand, version-aware, Cabinets)NoNoNoYes
Academic researchYes (6 providers)NoNoNoNo
Self-hostableYesNoNoNoYes
Free tierYes (open source)LimitedLimitedLimitedYes

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

Trust Model

This plugin implements TC-Local (machine-bound, single trust principal). See mcp-core/docs/TRUST-MODEL.md for full classification.

ModeStorageEncryptionWho can read your data?
stdio (default)~/.wet-mcp/config.jsonAES-GCM, machine-bound keyOnly your OS user (file perm 0600)
HTTP self-hostSame as stdioSameOnly you (admin = user)

License

MIT -- See LICENSE.

Ver o original no GitHub

Bom para

Relacionados