Wet MCP Server

Open-source MCP Server for web search, extract, crawl, academic research, and library docs with embedded SearXNG

Remote serverstreamable-httpPython

What is the Wet MCP server?

Connect Wet to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Open-source MCP Server for web search, extract, crawl, academic research, and library docs with embedded SearXNG. The wet mcp server is what makes that connection.

What the server does

  • 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
  • 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
  • Sync — -- Cross-machine sync of indexed docs via Google Drive (OAuth Device Code, no browser redirect)

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • search — Web (SearXNG metasearch), news, images, academic research (Scholar / arXiv / PubMed / CrossRef / Semantic Scholar / BASE), library docs (HyDE +
  • extract — URL -> smart chunks dict (clean_text + markdown + structured_data + code_blocks + metadata) via web-core 5-strategy chain. Batch processing (up to 50
  • 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

Credentials and setup notes

Configuration is passed through the environment: EMBEDDING_MODELS, RERANK_MODELS, LLM_MODELS, JINA_AI_API_KEY, GEMINI_API_KEY, PUBLIC_URL, GOOGLE_VERTEX_EXPRESS_API_KEY, OPENAI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Where it fits

This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Wet's toolset — search, extract, media and 3 more — is a fair guide to whether it matches your workflow.

This entry was verified against Wet's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
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)
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/XL
medialist (discover URLs from gallery pages), download (SSRF-safe). analyze was removed in v2.0.0 -- use imagine-mcp.understand instead
configstatus, set, cache_clear, docs_reindex, warmup, setup_sync, setup_status, setup_skip, setup_reset, setup_complete
helpPer-tool documentation: search, extract, media, config
config__open_relayRe-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.

How to install the Wet MCP server

{
  "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"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
EMBEDDING_MODELSConfiguration value read at startup.Optional
RERANK_MODELSConfiguration value read at startup.Optional
LLM_MODELSConfiguration value read at startup.Optional
JINA_AI_API_KEYCredential the server authenticates with.Yes
GEMINI_API_KEYCredential the server authenticates with.Yes
PUBLIC_URLEndpoint or connection string the server talks to.Yes
GOOGLE_VERTEX_EXPRESS_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Wet to search.
  • Use Wet to extract.
  • Use Wet to media.

Frequently asked questions

It connects Wet to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (search, extract, media, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Wet directly.