Ransack

io.github.chancewalker165-dotv1.0.0Updated Oct 7, 2026

Web search & fetch MCP for AI agents: 12 engines, one key, flat $15/mo at ransack.tools.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Ransack is a hosted MCP server that gives AI assistants live web search, page fetching, domain discovery, shopping lookups, YouTube transcripts, and cited…

What it does
It exposes a main ransack tool with modes for metasearch across twelve engines, page fetch, domain asset discovery, price and availability lookup, and claim verification, plus a youtube transcript tool. execute_research runs a multi-step discover, fetch, extract and synthesize pipeline into a cited report with per-claim citation verdicts, polled through tasks_get and retrieved with get_report. search_memory offers semantic recall over previously fetched page chunks. Results are engine-tagged and report coverage status and labelled walls instead of failing silently.
When to use it
Worth adding when an assistant needs current web information, source-backed answers, or cited research rather than model memory alone. Useful for gathering and verifying facts across many search engines, enumerating a domain's assets, or pulling YouTube transcripts. Less suitable if you only need occasional lookups or cannot accept a paid hosted dependency.
Requirements
A remote streamable-http endpoint at ransack.tools/mcp; no local runtime or package install. Requires a Bearer API key sent in the Authorization header, obtained from the provider's trial page. Network access to the hosted service is needed, and the free trial is limited to 14 days and 50 calls per day.
Before you install
It is a paid hosted service: $15 per month flat with 500 calls per day and 120 requests per minute after the trial, so usage costs money. The API key is a secret passed in the Authorization header and should be kept private. Queries and fetched URLs are sent to a third-party service, and research reports are persisted server-side and retrievable by report_id. Some paywalled, login-walled, or hard-blocked sites may return nothing or thin content.

Installation

In SourceWeft

  1. Open Ransack in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "ransack": {
      "type": "http",
      "url": "https://ransack.tools/mcp"
    }
  }
}

README

Ransack - Web Search & Fetch MCP Server for AI Agents

Ransack is an MCP server that gives AI agents live web search and page fetch through one endpoint and one API key. Twelve search engines behind a single MCP connection: search, fetch, discover, hosts, shop, verify, plus YouTube. No credits to manage, no per-engine billing: $15/month flat, 500 calls/day, failed fetches cost nothing, and every fetch returns a pass/fail receipt so silent failures cannot burn you.

This is a hosted service. This repository contains connection configuration, documentation, and logo; the server source is not public. Connect to:


   https://ransack.tools/mcp

Connect

Get an API key from ransack.tools/trial, then add the server to your client.

Claude Desktop

json
{"mcpServers":{"ransack":{"type":"streamable-http","url":"https://ransack.tools/mcp","headers":{"Authorization":"Bearer <API_KEY>"}}}}

Cursor

json
{"mcpServers":{"ransack":{"url":"https://ransack.tools/mcp","headers":{"Authorization":"Bearer <API_KEY>"}}}}

Pi / Cline / 5ire

json
{"mcpServers":{"ransack":{"type":"http","url":"https://ransack.tools/mcp","headers":{"Authorization":"Bearer <API_KEY>"}}}}

Transport is streamable-http; authentication is a Bearer API key.

Tools

ToolWhat it does
ransackThe main tool. Modes: search, fetch, discover, hosts, shop, verify, research. Markdown / JSON / hybrid output.
youtubeFetch a YouTube transcript from a video URL.
execute_researchMulti-step pipeline (discover, fetch, extract, synthesize) into a cited report with per-claim citation verdicts.
get_reportRetrieve a persisted report by report_id.
search_memorySemantic recall over previously fetched page chunks.
tasks_getPoll an asynchronous research task.

ransack

One tool, many modes: search, fetch, discover, hosts, shop, verify, research. search is metasearch across engines; fetch is the primary answer path; hosts enumerates a domain's assets from certificate transparency, DNS, sitemaps, web archives, crawl indexes, JS routes and scan records; shop returns price and availability; verify checks a claim against its cited sources. freshness bypasses the result cache; it does not date-filter, so results are not filtered by date.

youtube

Fetch a YouTube transcript from a video URL.

execute_research

Multi-step pipeline (discover, fetch, extract, synthesize) into a cited report. Returns a task handle by default; poll tasks_get for the report_id and its per-claim citation verdicts.

get_report

Retrieve a persisted report by report_id.

search_memory

Semantic recall over previously fetched page chunks.

tasks_get

Poll an asynchronous research task.

What you actually get back

  • Engine-tagged results. Every search result names the engine that found it, so you can tell Google from an independent index.
  • Coverage status, not silence. On hosts, every discovery engine reports ok, empty, timeout or skipped. Found-nothing is never indistinguishable from tried-and-failed.
  • Labelled walls. [bot wall: <vendor>] and [dead page: HTTP 404] come back as labels. Pages the server cannot read are reported, not guessed.
  • Per-claim citation verdicts. Research reports carry a verdict per claim, checked against the sources actually retrieved.
  • No query rewrites. Ever. The caller owns site selection. Ransack never appends operators to your query or silently changes what you asked for.
  • One key, six tools. Search, fetch, discovery, shopping, transcripts and cited research behind a single endpoint.

Honest limitations

  • Paywalled and login-walled pages (e.g. some news, GitHub /commits views) can't always be read.
  • Retailers that hard-block scraping (Amazon, Walmart) may return nothing rather than guessed data.
  • TikTok is searchable, and the result snippet already carries the caption. The reader tier returns the caption, creator handle, post date and engagement counts, but the video, the comments and the spoken transcript do not come back, and the browser tier can return only TikTok's "Page not available" stub.
  • search fast-lane results are partial by design; fetch is the primary answer path.
  • Labelling is not guaranteed: a wall sometimes comes back as thin page content instead.

Pricing

  • Trial: free for 14 days, 50 calls/day, no card (ransack.tools/trial).
  • Paid: $15/month flat, 500 calls/day, 120 requests/min.

License

This repository is documentation and configuration only. The service at ransack.tools is proprietary.

Source: README.md at commit ff39b24

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 7, 2026