Wet MCP

Web search, content extraction, and library docs for AI agents -- 5-strategy scraping, runs without API keys. Its 6 documented tools cluster into config, read & search, extract, media. It runs locally over stdio via the published package.

People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-24 · ★ 16 · #11 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

Apache-2.0 · Python servers · how we verify → /methodology

01 · Install Wet MCP

before you install - you'll need

Set EMBEDDING_MODELS, RERANK_MODELS, LLM_MODELS, JINA_AI_API_KEY, GEMINI_API_KEY, MCP_TRANSPORT, PUBLIC_URL before connecting.

Claude Code

claude mcp add n24q02m-wet-mcp -- uvx wet-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "n24q02m-wet-mcp": {
      "command": "uvx",
      "args": [
        "wet-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · container (OCI image) - can be sandboxed away from your filesystem

license Apache-2.0 - declared in the repository

pypi package wet-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.n24q02m is GitHub-verified and matches the repo owner

03 · What Wet MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

An agent gets 6 documented tools across config, read & search, extract, including search, extract, media, config.

Capability map

Tools grouped from the project's README - what Wet MCP lets an agent do.

Config

2 tools - e.g. status, set, cache_clear, docs_reindex, warmup, setup_sync, setup_status, setup_skip, setup_reset, setup_complete; Re-trigger the zero-config relay setup flow (prints a fresh relay URL for the browser…

config · config__open_relay

read & search

1 tool - e.g. Web (SearXNG metasearch), news, images, academic research (Scholar / arXiv / PubMed / CrossRef / Semantic Scholar / BASE), library docs (HyDE + FTS5), find simi

Extract

1 tool - e.g. URL -> smart chunks dict (clean_text + markdown + structured_data + code_blocks + metadata) via web-core 5-strategy chain. Batch processing (up to 50 URLs), dee

extract

Media

1 tool - e.g. list (discover URLs from gallery pages), download (SSRF-safe). analyze was removed in v2.0.0 -- use imagine-mcp.understand instead

media

Help

1 tool - e.g. Per-tool documentation: search, extract, media, config

help

Latest releases

v3.7.3 · 2026-08-14

update python:3.13-slim-bookworm Docker digest to 00faa2d · update @cloudflare/workers-types to ^5.20260804.1 · lock file maintenance · isolate search quality harness from legacy drive credentials · bump wet dependency…

v3.7.2 · 2026-08-11

v3.7.2 (2026-08-11) · _This release is published under the Apache-2.0 License._ · --- · Detailed Changes: v3.7.2-beta.1...v3.7.2

v3.7.1 · 2026-08-11

v3.7.1 (2026-08-11) · _This release is published under the Apache-2.0 License._ · --- · Detailed Changes: v3.7.1-beta.1...v3.7.1

04 · Who maintains Wet MCP

wet-mcp is maintained by n24q02m. We track 9 MCP servers from n24q02m - 9 actively maintained, 209 combined GitHub stars, oldest repo from Dec 2025. Full record: all servers from n24q02m.

05 · Facts

repository: github.com/n24q02m/wet-mcp
category: web scraping - ranked #11 of 78 actively-maintained web scraping servers as of 2026-08-25.
release cadence: 4 releases in the last 90 days (latest 2026-08-14)
registry: io.github.n24q02m/wet-mcp (active, first published 2026-03-06 · 53 versions)
packages: pypi:wet-mcp · oci:docker.io/n24q02m/wet-mcp:latest

06 · Wet MCP FAQ

Is Wet MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-24 and it shipped 4 releases in the last 90 days. We re-verify nightly.

What can Wet MCP do?

An agent gets 6 documented tools across config, read & search, extract, including search, extract, media, config.

How do I install Wet MCP?

Run `uvx wet-mcp`. The README documents 7 environment variables (EMBEDDING_MODELS, RERANK_MODELS, LLM_MODELS…) to set first. Set EMBEDDING_MODELS, RERANK_MODELS, LLM_MODELS, JINA_AI_API_KEY, GEMINI_API_KEY, MCP_TRANSPORT, PUBLIC_URL before connecting. You can also paste the ready-made client config above.

Does Wet MCP run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Wet MCP

Alternatives to Wet MCP

Maintained web scraping servers if Wet MCP isn't the fit.

Pairs well with

Servers that cover what Wet MCP doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Getregdata · Proxy4agents MCP · Octen MCP · Scraper · Outscraper MCP Server

More Python MCP servers · Server Malcolm · WhatsApp MCP Server · Nalegalu MCP · Pdfmux · Legislative Yuan · see all