Name: Spoofy
Author: spoofy

Spoofy MCP

Quote and order followers, views, likes and members for any public link, with spend caps.

Tool-list grade A Remote · Streamable HTTP OAuth 2.1 15 tools v1.2.0

No reviews yet by spoofy The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Quote and order followers, views, likes and members for any public link, with spend caps.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http spoofy-mcp https://spoofy.social/mcp

# 2 — ask your agent for something these tools do
#   find_services, get_quote, place_order and 12 more

Spoofy costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

spoofy1 server

1 category

All 1 server

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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.

Claude Codedeclared by this listing

This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Its publisher asks you to sign in with OAuth: run /mcp in Claude Code and pick this server, and it opens a browser for that once.

claude mcp add --scope user --transport http spoofy-mcp https://spoofy.social/mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — the only sign-in is its publisher’s own, with OAuth.

What it asks of you

Nothing is required, but it can take Authorization header (Your Spoofy API key as a Bearer token, from https://spoofy.social/app/developers?utm_source=mcp-registry&utm_medium=listing&utm_campaign=mcp — or leave it out and sign in with your Spoofy account when your client supports OAuth. Connecting and listing the tools work without either.) if you want to set it.

What it writes

One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.

What you approve

15 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.

Only tools that write or reach the network

Find what Spoofy can do for a link or a goal, with prices. ALWAYS call this first: service ids come from here. Give link (any profile, post, video, channel, group, token page or website URL) and/or goal in plain words, e.g. "500 followers on my tiktok" or "cheap views for this YouTube video". With a link you only get services that fit that exact link (a profile link gets followers, a post link

Parameter	Type	Required	Notes
link	string	no	The URL to grow, e.g. https://x.com/yourname or https://www.tiktok.com/@you/video/123.
goal	string	no	What the user wants in words, e.g. "1k followers", "2.5k views, cheapest", "telegram members".
query	string	no	Optional words every service returned must match: a country or region ("usa", "europe"), a quality ("real", "premium"), a kind ("story", "reels").
limit	integer	no	Most services to return (default 8).

Exact price in USD for a quantity of one service (from find_services). Checks the quantity is within the service range. Free; spends nothing. Use it to tell the user the cost before place_order. For services with an input, pass the same inputs as for place_order; the quantity is then the units charged: the number of comments or usernames, per run × runs, or for subscriptions max × (posts + old

Parameter	Type	Required	Notes
service	integer	yes	Service id from find_services.
quantity	integer	yes	How many units (followers, views, …).
link	string	no	Optional: the link it is for.
inputs	object	no	Order fields, for services with an input (see find_services).

Place an order. THIS SPENDS THE USER'S REAL BALANCE (USD) and starts delivery to the link; it cannot be undone except by cancel_order where the service allows it. Before calling: get the price with get_quote and get the user's explicit agreement to that price. Then call with confirm: true. Without confirm: true nothing is charged and you get the price back so you can ask. dry_run: true valid

Parameter	Type	Required	Notes
service	integer	yes	Service id from find_services.
link	string	yes	The URL to deliver to. Must fit the service (e.g. a profile link for followers).
quantity	integer	no	How many units. Leave out where the inputs count it (comments, usernames) or it is fixed (packages, subscriptions).
inputs	object	no	Order fields, for services with an input (see find_services).
confirm	boolean	no	Must be true to actually place and charge. Only after the user agreed to the price.
dry_run	boolean	no	true = validate and price only, never charge.
idempotency_key	string	no	Unique string per intended order; a retry with the same key returns the first order.

Place up to 25 orders in one go — several services, one link or several — paid together from the balance. THIS SPENDS THE USER'S REAL BALANCE (USD) and starts delivery. Use it when the user wants several things at once (e.g. followers + likes + views for one account); for one order use place_order. Every order is checked first at today's price: if any one cannot go (link does not fit, quantity out

Parameter	Type	Required	Notes
items	array	yes	The orders, up to 25.
confirm	boolean	no	Must be true to actually place and charge. Only after the user agreed to the total.
dry_run	boolean	no	true = check and price only, never charge.
max_total	string	no	The total in USD the user agreed to, e.g. "12.34": nothing is placed if today's prices come to more.
idempotency_key	string	no	Unique string per intended batch; a retry with the same key returns the first orders.

Status and progress of one order: status (pending, processing, completed, partial, refunded, cancelled, failed), start count, delivered, remains, charge and refunds in USD, and whether it can be cancelled now.

Parameter	Type	Required	Notes
order	integer	yes	The order number (the id field of an order, e.g. 1042).

The user's orders, newest first. Filter by status; page with before = the smallest order number already seen.

Parameter	Type	Required	Notes
status	string	no	Only orders in this status.
limit	integer	no	How many (default 10, max 50).
before	integer	no	Only orders with a smaller number than this.

Ask to cancel a pending or processing order (only when the order says cancelable: true). Whatever was not delivered is refunded to the balance in USD. Confirm with the user first.

Parameter	Type	Required	Notes
order	integer	yes	The order number (the id field of an order, e.g. 1042).

The user's spendable balance in USD. Orders are paid from it.

No parameter schema on file.

How the user adds money to the balance: stablecoins (USDC, USDT or USDG, on the networks that are on) sent to their own deposit address — one address for every EVM network, another on Solana — credited 1 coin = $1, plus the top-up page link. Use it when an order fails with insufficient_balance. Tell the user to send only the listed coin on the listed network. You cannot move money yourself — give

No parameter schema on file.

Set up an automation: Spoofy places ordinary orders for the user on a plan. Kinds: spread (a total over time, e.g. {"kind":"spread","service":12,"link":"…","quantity":10000,"over":"3d"}; pace "steady" or "front" for an S-curve growth plan), scheduled (one order at start_at), recurring (every "1d"/"6h"/"1w", optional at "14:00" + timezone, with times, until or budget), split (past one order's max),

Parameter	Type	Required	Notes
automation	object	yes	The automation, exactly as POST /api/v1/automations takes it: {"kind": …, "service": …, "link": …, …}.
confirm	boolean	no	Must be true to actually create it. Only after the user agreed to the plan and its cost.
dry_run	boolean	no	true = plan and price only, create nothing.
idempotency_key	string	no	Unique string per intended automation; a retry with the same key returns the first one.

The user's automations, newest first, with progress (runs placed, delivered), spend against budget and the next run. Filter by status.

Parameter	Type	Required	Notes
status	string	no	Only automations in this status.
limit	integer	no	How many (default 10, max 50).

One automation with its timeline: every run, the order it placed and what that delivered, or why a run waits or was skipped (balance, budget, a daily limit).

Parameter	Type	Required	Notes
automation	integer	yes	The automation number (the id of an automation, e.g. 2001).

Stop placing new runs until it is resumed (orders already running keep delivering). Nothing is charged while paused.

Parameter	Type	Required	Notes
automation	integer	yes	The automation number (the id of an automation, e.g. 2001).

Carry on with a paused automation: the rest of the plan moves by the time it was paused. After a price change, resuming accepts the new price for the runs left — tell the user first.

Parameter	Type	Required	Notes
automation	integer	yes	The automation number (the id of an automation, e.g. 2001).

Stop an automation for good: every future run is cancelled. Orders already running finish, unless cancel_running: true asks those that allow it to cancel too (the undelivered part is refunded). Confirm with the user first.

Parameter	Type	Required	Notes
automation	integer	yes	The automation number (the id of an automation, e.g. 2001).
cancel_running	boolean	no	Also ask its running orders to cancel.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Spoofy or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.2.0 · scanned 28 Oct 2026

Graded from the tools this server lists, not from its source code.

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 score93

Findings0 threat · 1 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digest2938f59bb03caeed0a277f09e5178095244996379f14854b26a6616a8131b74f

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

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.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

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
find_services	no tags
get_quote	no tags
place_order	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
place_orders	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
get_order	no tags
list_orders	no tags
cancel_order	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
get_balance	no tags
get_top_up_info	no tags
create_automation	untrusted-inputexternal-sink	untrusted-input: keyword "rss"; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
list_automations	no tags
get_automation	no tags
pause_automation	state-write	state-write: declares readOnlyHint: false
resume_automation	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
cancel_automation	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, 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 digest2938f59bb03caeed

Scanned2026-10-28

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.