mcpField
L
Levirge Search

Levirge Search

Remote
search.levirge.comSearch0Updated 2w ago
RepositoryVisit website

About Levirge Search

Levirge Search is a hosted web-research MCP server for agents. It searches across engines and fetches source pages, using a browser when pages require JavaScript or reject ordinary requests.

Key features

  1. 01Multi-engine web search
  2. 02Browser-backed URL fetching
  3. 03Asynchronous URL scans
  4. 04Per-tenant stealth-domain registry
  5. 05Report blocked stealth-browser domains
  6. 06Research and fetch commands

Use cases

  1. 01Find web sources across search engines
  2. 02Read JavaScript-dependent pages
  3. 03Fetch many URLs in the background
  4. 04Retry sites that block ordinary requests

MCP support

Provides MCP tools for web search, URL fetching, background scans, and fetch-result retrieval.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://search.levirge.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Levirge Search

version

Levirge Search — web research your agent can actually reach

Search the web and read the sources, with citations.

Levirge Search is a hosted MCP server for research: unfiltered web search, and a URL fetch where pages that need JavaScript or refuse plain requests are opened in a full browser — so your agent can open the original source and cite it.

Install (2 minutes)

Claude Code:

claude plugin marketplace add levirge/search
claude plugin install levirge-search@levirge-search

Then run /mcp in a session and sign in.

Codex CLI:

codex plugin add levirge/search

Any other MCP client — point it at https://search.levirge.com/mcp. It answers a standard OAuth challenge, so clients that speak MCP authorization discover sign-in on their own; no token to paste.

Update

plugin install won't upgrade, and the desktop "Update" button stays greyed out until the app's marketplace cache is refreshed (the dialog has no refresh button). From the CLI — it shares the same store as the desktop app:

claude plugin marketplace update levirge-search
claude plugin update levirge-search@levirge-search

Then restart the client — the plugin registry and MCP tool schemas are cached at startup, so new commands and tool params don't appear until then.

What you get

  • Search that isn't a summary — search runs SearXNG across engines and returns real result sets, not one provider's ranking.
  • Fetch that opens the page — fetch takes any URL, including agent-constructed API endpoints; pages that need JavaScript or refuse plain requests are opened in a full browser. One tool, both routes.
  • Background scans — fetch_async queues up to 200 URLs through the same routing and paces them per-domain; collect with fetch_results instead of blocking.
  • A stealth registry that learns — domains that needed the full browser are remembered per tenant, so the second visit skips the retry (/levirge-search:stealth).
  • A failure queue worth reading — stealth_failures lists domains where the stealth browser itself got blocked, including regressions on domains that used to work.
  • A skill that fires on refusal — web-fetch-fallback teaches the agent to reach for this when its primary fetch says "blocked", instead of silently falling back to search.

Commands

CommandDoes
/levirge-search:researchMulti-query search, fetch the top hits, synthesize with sources
/levirge-search:fetchFetch one URL via routed fetch and summarize it
/levirge-search:stealthList stealth-required domains, or register one

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.