hermes-web-mcp
Provides keyless web search using DuckDuckGo as a fallback search engine, returning titles, URLs, and snippets for search results.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
hermes-web-mcp
Web powers for any MCP client — no API keys required.
hermes-web-mcp is an MCP (Model Context Protocol) server that gives DSH Desktop and any MCP client a complete web toolkit:
web_search — keyless search via cn.bing direct, with a DuckDuckGo-over-proxy fallback; no search API key needed.
web_extract — scrape any page with full JS rendering (local playwright-service + html-to-md chain over dual CDP Chrome) and return clean Markdown.
7 × page_* — real browser automation on a shared CDP Chrome inside an isolated context (never touches your host browser tabs):
page_open,page_click,page_type,page_read,page_shot,page_back,page_close.
Tools
Tool | Purpose | Key arguments |
| Keyless web search (cn.bing direct, DDG fallback) → title/URL/snippet list |
|
| Render + scrape a page to Markdown via playwright-service + html-to-md; dual-CDP failover, then plain-fetch degrade |
|
| Open a URL in the shared CDP Chrome; returns the first 4000 chars of body text |
|
| Click an element matched by a CSS selector |
|
| Fill an input field (optionally press Enter) |
|
| Read up to 12000 chars of the current page body | — |
| Screenshot the current page into |
|
| Navigate back one page | — |
| Close the isolated browser context (cleanup) | — |
9 tools in total: web_search + web_extract + 7 page_* tools.
Related MCP server: @domscout/mcp
How it works
┌──────────────┐ stdio (MCP) ┌────────────────────── hermes-web-mcp ──────────────────────┐
│ MCP client │ ───────────────▶ │ web_search → cn.bing (keyless) / DDG fallback │
│ (DSH, etc.) │ │ web_extract → playwright-service (:3003) → html-to-md │
└──────────────┘ │ (:8080) ⇄ CDP Chrome 9333 (direct) / │
│ 9334 (via HTTP proxy) │
│ page_* → playwright chromium.connectOverCDP │
└───────────────────────────────────────────────────────────┘web_extract never needs a scraper API key: a local playwright-service renders the page over CDP, and an html-to-md service converts the HTML to Markdown. Two Chrome instances back it:
CDP direct (default,
127.0.0.1:9333) — for domestic sites and pages where your normal login session lives.CDP proxied (
127.0.0.1:9334) — Chrome with traffic routed through your local HTTP proxy, for overseas/restricted sites.
web_extract tries your preferred CDP first and fails over to the other automatically; if both fail it degrades to a plain fetch (no JS rendering). The page_* tools use Playwright's connectOverCDP against the same shared Chrome in an isolated context — host tabs are never touched.
Environment variables
Variable | Default | Meaning |
|
| Path to a Playwright install whose |
|
| playwright-service scrape endpoint (POST |
|
| html-to-md endpoint (POST |
|
| CDP endpoint of the direct Chrome |
|
| CDP endpoint of the proxied Chrome |
All variables are optional — omit them and the defaults above are used.
Prerequisites (deployment)
Node.js ≥ 22, then
npm installin this repo (only runtime dependency:@modelcontextprotocol/sdk).playwright-service — a local service exposing
POST /scrape{url, wait_after_load, cdp_url}→{content, pageStatusCode, contentType}, rendering the page with Playwright against the target CDP. (The firecrawl-lite project has a reference implementation.)html-to-md — a local service exposing
POST /convert{html}→{markdown}.Two CDP Chrome instances:
chrome --remote-debugging-port=9333(direct)chrome --remote-debugging-port=9334launched with traffic routed through your local HTTP proxy (for sites not directly reachable).
A Playwright install resolvable at
WEBMCP_PW(or the default path) for thepage_*tools.
The defaults assume services on
127.0.0.1:3003/127.0.0.1:8080and Chrome on9333/9334. Different setup? Just set the env vars.
Registering the server
Generic MCP config (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"hermes-web": {
"command": "node",
"args": ["D:/path/to/hermes-web-mcp/hermes-web-mcp.js"],
"env": {
"WEBMCP_PW": "D:/path/to/playwright-service/node_modules/playwright",
"WEBMCP_SCRAPE": "http://127.0.0.1:3003/scrape",
"WEBMCP_CONVERT": "http://127.0.0.1:8080/convert",
"WEBMCP_CDP_DIRECT": "http://127.0.0.1:9333",
"WEBMCP_CDP_PROXY": "http://127.0.0.1:9334"
}
}
}
}dsh-mcp-client (SQLite registry, insert example — adapt column names to your schema):
INSERT INTO mcp_servers (name, command, args, env) VALUES (
'hermes-web',
'node',
JSON_ARRAY('D:/path/to/hermes-web-mcp/hermes-web-mcp.js'),
JSON_OBJECT(
'WEBMCP_PW', 'D:/path/to/playwright-service/node_modules/playwright',
'WEBMCP_SCRAPE', 'http://127.0.0.1:3003/scrape',
'WEBMCP_CONVERT', 'http://127.0.0.1:8080/convert',
'WEBMCP_CDP_DIRECT', 'http://127.0.0.1:9333',
'WEBMCP_CDP_PROXY', 'http://127.0.0.1:9334'
)
);Smoke test
With all prerequisites running:
npm install
node smoke.jssmoke.js spawns the server over real MCP stdio, lists the registered tools, then calls web_search, web_extract, page_open (proxied) and page_shot, printing each output. It requires the playwright-service, the html-to-md service and both CDP Chrome instances to be up.
License
MIT — Copyright (c) 2026 ShadowMiner.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Scrape, crawl and search the web for AI agents via MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides a headless Chromium browser through MCP, enabling AI agents to browse JavaScript-rendered pages, search the web, capture screenshots, extract tables and data, and run stateful multi-step interactions like clicking, typing, and form submission.2,465,065 npm1MIT
- AlicenseAqualityCmaintenanceEnables browser automation and web data extraction through MCP tools, including Markdown reading, screenshots, structured data extraction, page inspection, and allowlisted site crawling.1061 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to scrape, crawl, map, search, and extract web pages as clean markdown or structured JSON directly through MCP tools.AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents and LLM apps to run live web searches and fetch public web pages as Markdown, returning structured search results and page content through MCP clients.1Apache 2.0