Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
Nothing to run from here
Hashscraper is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
10
downloads a day
local
runs on your machine
443
downloads in 30d
What it does
Coupang top 30 and public web data bots (Naver, Instagram, Olive Young, maps, reviews) for AI agents
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user hashscraper-mcp '--' npx -y @hashscraper/mcp
# 2 — ask your agent for something these tools do
# login, me, catalog and 4 more
Hashscraper costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
HAAll 1 server
hashscraper1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Hashscraper as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user hashscraper-mcp '--' npx -y @hashscraper/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take HASHSCRAPER_API_KEY (Optional. A HashScraper API key from My page -> API. Without it, use the login tool once to connect in the browser.) if you want to set it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Connect the user's HashScraper account in the browser (device login, free sign-up included). Use it first when another HashScraper tool says "Not connected", or when the user asks to connect or reconnect.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| restart | boolean | no | Throw away a waiting login and start a new link. |
Show the connected account's email and how many daily free credits are left today (they refill at midnight KST). Use before a paid-looking collection to check what is free.
No parameter schema on file.
Search the built-in list of 120+ ready-made data bots (Coupang, Naver blog/cafe/news/shopping/maps, Instagram, YouTube, Olive Young, Musinsa, Kurly, KREAM, Google/Kakao maps, app stores, community boards …).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search | string | no | Text to look for in site, bot name, summary and inputs, e.g. "coupang", "naver blog", "reviews". |
Collect public web data with one HashScraper bot (find the worker with catalog first) and return the rows — e.g. a Coupang product page's price, 50 Naver blog posts for a keyword, reviews, map places.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| worker | string | yes | Worker name from catalog, e.g. "DemoCoupangDetailWorker". |
| inputs | object | no | Bot inputs: keys are "param1"… or the input name / English name from catalog; values are text (several URLs or keywords: an array or one per line). Omitted inputs use the bot's saved settings. |
| use_credits | boolean | no | Set true only if the user wants to spend their own credits after today's free credits are used up. |
| accept_terms | string | no | The data terms version the user was shown and clearly agreed to (e.g. "v0.2"). Only set it after the user agrees; never agree for the user. |
| wait_seconds | integer | no | How long to wait for the collection in this call (default 45, max 55). If it is not finished, the answer says to call fetch later. |
| max_rows | integer | no | Return at most this many rows in the answer (default 100). The summary always shows the total. |
| csv_path | string | no | Absolute path ending in .csv. Saves ALL rows to this file (UTF-8 with BOM, opens in Excel) instead of returning them in the answer. |
Get the rows of an earlier run by dataset id (from run). Use it when run said the collection was still going. Waits up to wait_seconds if it is still collecting. Reading rows costs nothing extra.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataset_id | integer | yes | Dataset id returned by run. |
| wait_seconds | integer | no | How long to wait for the collection in this call (default 45, max 55). If it is not finished, the answer says to call fetch later. |
| max_rows | integer | no | Return at most this many rows in the answer (default 100). The summary always shows the total. |
| csv_path | string | no | Absolute path ending in .csv. Saves ALL rows to this file (UTF-8 with BOM, opens in Excel) instead of returning them in the answer. |
List the Coupang categories whose daily best-selling top 30 is ready, with the latest snapshot date. Free. Use it to answer "which categories can you rank?" or to pick the right category for coupang_top.
No parameter schema on file.
Use when the user wants today's best-selling / top 30 products of a Coupang category with price, reviews, delivery and detail-page columns (sale price, coupons, seller type, monthly buyers …), or a price comparison of its top products.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | yes | Category id (e.g. "429888") or name (e.g. "커피믹스"). See coupang_categories. |
| limit | integer | no | Rows 1-30 (default 30). The price is the same. |
| use_credits | boolean | no | Set true only if the user wants to spend their own credits after today's free credits are used up. |
| accept_terms | string | no | The data terms version the user was shown and clearly agreed to (e.g. "v0.2"). Only set it after the user agrees; never agree for the user. |
| csv_path | string | no | Absolute path ending in .csv. Saves ALL rows to this file (UTF-8 with BOM, opens in Excel) instead of returning them in the answer. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Hashscraper or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.1.0 · scanned 30 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digesta9e5c88034ec02aefbcfd89815a22b92a62290444a9a0241137adb12c80f794b
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (7 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| login | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| me | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| catalog | no tags | |
| run | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| fetch | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| coupang_categories | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| coupang_top | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digesta9e5c88034ec02ae
Scanned2026-10-30
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Hashscraper can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.