Skip to content

GrowVib: Social Media Growth MCP server

com.growvib/growvibgrowvib.comstreamable-httpv0.4.0Scanned

Discover, compare and buy social media growth (Instagram, TikTok, YouTube, Telegram, X); x402 ready

9 tools: 1 can delete or cancel things, 3 change things and 5 only read.

Tools: 1 delete, 0 irreversible, 3 write, 5 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the GrowVib: Social Media Growth MCP server can do

The GrowVib: Social Media Growth MCP server is published by growvib.com, a domain the MCP Registry verified. It has 9 tools. It can delete or cancel things (1 tool: create_paid_order) and create or change data (3 tools: create_checkout, recommend_service and search_catalog). 5 tools only read.

2 tools bring in text other people can write (create_checkout and create_paid_order).

The fixed checks matched 2 findings (long-description and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 0.4.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

9 tools

Deletes or cancels 1Claude Code: deny
  • create_paid_orderPlace an order and pay for it with USDC on Base or Solana, with no GrowVib account and no human in the loop, using the x402 payment protocol.Reads text others writeNo findings

    Why it is in this group

    • The name "create_paid_order" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Place an order and pay for it with USDC on Base or Solana, with no GrowVib account and no human in the loop, using the x402 payment protocol. Call it FIRST without the `payment` argument: it returns the exact payment requirements, one `accepts` entry per network (amount in atomic units, asset, recipient, network, and for Solana the facilitator's feePayer). Pick the network your wallet is on: sign an EIP-3009 transferWithAuthorization (Base) or build and sign the USDC transfer transaction (Solana) for exactly those requirements, then call it AGAIN with the same arguments plus `payment` set to the signed x402 payment payload. Anything paid above the order's price stays as spendable balance on the wallet's account, so many small orders can be paid for with one settlement. If a call reports that the payment is still being confirmed, do NOT sign and send a new payment: the first one may already have gone through. Use get_quote first if you only want a price.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
Changes things 3Claude Code: ask
  • create_checkoutCreate a checkout session: a payment link a PERSON opens and pays in their own USDC wallet (Base or Solana), for when you cannot sign a payment yourself or the user wants to pay wi…Reads text others writeNo findings

    Why it is in this group

    • The name "create_checkout" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Create a checkout session: a payment link a PERSON opens and pays in their own USDC wallet (Base or Solana), for when you cannot sign a payment yourself or the user wants to pay with their own wallet. Pick the service with search_catalog or recommend_service and price it with get_quote first, then call this with service_id, quantity and link. The result carries page_url (give it to the person), the exact amount, expires_at (the price is held until then, 30 minutes by default) and a token for get_checkout_status. Creating a session moves no money and reserves nothing: nothing is charged until the person signs in their wallet, and an unpaid session simply expires. Each call opens a NEW session, so call it once per intended order and reuse the token you were given. Prefer create_paid_order when you hold a wallet and should pay yourself.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • recommend_serviceChoose WHICH plan option to order, once you know what to buy and for how many.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description is 2,653 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...son will pay in their own wallet instead (listed while checkout sessions are on)."

      What this check looks for
    Description, as the server wrote it
    Choose WHICH plan option to order, once you know what to buy and for how many. Use it instead of comparing options yourself from search_catalog or get_service. Takes a service (or a platform plus a goal), a quantity, an audience and a preference. Returns one recommended option plus the cheapest, highest-tier and fastest-listed alternatives. Each pick carries the price per 1000, the total for this quantity, the quantity range it accepts, its quality tier, typed axes such as country or watch length, the listed delivery speed and start window, a sensitive flag marking a deliberate product such as a negative reaction, and short reasons written for the buyer. Branch on the typed fields; the reasons are prose in the requested locale and state only what an option gives, so their absence is never a drawback. One reason states how many independent delivery pools can serve the option, when two or more can: it is a count of the ways we can deliver it, not a promise about any one order, and a pick without it is not worse. The response also says how many options were considered, how many fit, and why the rest fell out (rejected: audience_mismatch, quantity_below_min, quantity_above_max, dominated). It carries quoted_at and catalog_version: the version fingerprints THIS service's option data the answer came from, so it differs between services and is only comparable with another answer for the same service. If you recommend, ask the user, then order, re-call for that service and compare catalog_version to know whether the card changed in between. Prices are live at order time; placing an order re-prices from the same data get_quote does, so treat quoted_at as when this answer was computed, not as a price hold. tradeoffs compares each alternative with the lead as data (price and total deltas, quality steps, listed speed ratio, start bucket delta, max quantity delta, plus gives and costs naming the dimensions it wins and loses on; null means one side lists nothing). Use it to CHOOSE and to explain a choice as what each option gives ("$18.60 less for one tier lower and twice the listed rate"); never present a pick to the user as a percentage more expensive than another. Identify the service by service_id (from search_catalog) OR by platform + goal (the deliverable, e.g. platform "youtube" and goal "short-views" or "followers"). Read-only: it places no order. Pass the returned option_id as service_option_id to get_quote and create_paid_order (this endpoint lists it while the accountless x402 payment channel is on), or create_checkout when a person will pay in their own wallet instead (listed while checkout sessions are on).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_catalogSTART HERE when you do not yet know which service to buy: this is the entry point to the catalog.1 finding

    Why it is in this group

    • The name "search_catalog" says "search": a word for reading.
    • The description's first verb is "start": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "search_catalog" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "search_catalog" says "search": a word for reading.

      What this check looks for
    Description, as the server wrote it
    START HERE when you do not yet know which service to buy: this is the entry point to the catalog. Already have a service id? get_service returns that one in full detail. Know the service and only need the right plan for a quantity? recommend_service picks one. Searches the sellable social growth service catalog (Telegram, Instagram, TikTok, YouTube and more). Each result includes the service (id, name, platform, starting/cheapest price per 1000) AND up to 8 of its plan options (plain options first, the recommended first among them, each with id, name, price per 1000, min/max quantity; options_total says how many there are and get_service returns them all) - present the options to the user and let them choose a plan, then pass that service_option_id to get_quote and create_paid_order (this endpoint lists it while the accountless x402 payment channel is on), or create_checkout when a person will pay in their own wallet instead (listed while checkout sessions are on) instead of defaulting to the cheapest.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 5Show 5 read-only tools
  • get_checkout_statusRead a checkout session created with create_checkout: its status (open, pending, paid, paid_no_order, failed, expired), the frozen quote, and once paid the payment and the order wi…No findings

    Why it is in this group

    • The name "get_checkout_status" says "get": a word for reading.
    Description, as the server wrote it
    Read a checkout session created with create_checkout: its status (open, pending, paid, paid_no_order, failed, expired), the frozen quote, and once paid the payment and the order with its tracking code. Poll it after handing the person the link, every few seconds, until it reports paid or expired. `pending` means a payment is being confirmed: tell the person to wait, never to pay again. `paid_no_order` means the money arrived as balance on the paying wallet's account but the order could not be placed; the person was told to contact support. Read-only and idempotent, so polling is safe.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_paid_order_statusTrack an order placed with create_paid_order: status, start count and remaining quantity, plus a delivery block (the start window the option lists, its bound in minutes, whether de…No findings

    Why it is in this group

    • The name "get_paid_order_status" says "get": a word for reading.
    Description, as the server wrote it
    Track an order placed with create_paid_order: status, start count and remaining quantity, plus a delivery block (the start window the option lists, its bound in minutes, whether delivery has started, and start_overdue when an active order has not started past that bound). Delivery is gradual once it starts and completion time is not estimated, so a falling remains is progress, not a stall. The progress fields come from a periodic check that can trail the target by minutes; status_checked_at says when it last ran. Pass the `agent_token` that create_paid_order returned (or one from the wallet sign-in at POST /v1/agent/auth/challenge). Read-only and idempotent, so polling it is safe. Statuses: PENDING, SUBMITTED, PROCESSING, COMPLETED, PARTIALLY_COMPLETED, CANCELED, FAILED, PARTIALLY_FAILED, REFUNDED, PARTIALLY_REFUNDED.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_quoteGet the exact price that will be charged, with no account needed.No findings

    Why it is in this group

    • The name "get_quote" says "get": a word for reading.
    Description, as the server wrote it
    Get the exact price that will be charged, with no account needed. Call this before every order: never total up the per-1000 prices the catalog tools return yourself, because the quantity bounds and rounding are applied here and nowhere else. Returns unit price and total in USD, priced by the same server-side path a real order uses. It places no order and charges nothing. The result's payment_methods says how the order can be paid: from a connected GrowVib account (connect one over OAuth at the /mcp endpoint, which is where the account ordering tool lives), or, when listed, with no account at all over x402 (USDC on Base or Solana, via create_paid_order or the REST endpoint it names; payment_methods.x402.networks lists the rails).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_serviceLook up ONE service you already have the id for.No findings

    Why it is in this group

    • The name "get_service" says "get": a word for reading.
    Description, as the server wrote it
    Look up ONE service you already have the id for. No id yet? Find one with search_catalog. Want a single option chosen for a quantity rather than all of them? Use recommend_service. Returns the service's full detail, including ALL of its plan options (id, name, price per 1000, min/max quantity, quality tier, typed axes such as country or watch length, listed delivery speed and start window, and the recommended flag), so you can present the available plans and quantity range to the user, then pass the chosen service_option_id to get_quote and create_paid_order (this endpoint lists it while the accountless x402 payment channel is on), or create_checkout when a person will pay in their own wallet instead (listed while checkout sessions are on).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_paid_ordersList the orders belonging to the wallet behind an agent_token, newest first, each with the same fields get_paid_order_status returns.No findings

    Why it is in this group

    • The name "list_paid_orders" says "list": a word for reading.
    Description, as the server wrote it
    List the orders belonging to the wallet behind an agent_token, newest first, each with the same fields get_paid_order_status returns. Use it when you no longer have the order_id an order gave you: after a restart, when resuming work another session started, or to check everything this wallet has bought. Pass the `agent_token` from any of its orders (or from the wallet sign-in at POST /v1/agent/auth/challenge). Optional `status` narrows to one order status, `page` and `page_size` page through the rest (page_size defaults to 10 and is capped at 100; the result carries the total so you know when to stop). Read-only and idempotent, so polling it is safe.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:39 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://api.growvib.com/.well-known/oauth-protected-resource
Authorization servers
https://api.growvib.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 destructive, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.growvib.com/mcp-public: tools/list returned 9 tools to an anonymous client, including create_paid_order (destructive), create_checkout (write), recommend_service (write), search_catalog (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info
  • The server marks "search_catalog" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "search_catalog" says "search": a word for reading.

    What this check looks for
  • The description is 2,653 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...son will pay in their own wallet instead (listed while checkout sessions are on)."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools7 changed.~7 changedView diff
  2. Tools3 changed.~3 changedView diff
  3. Tools1 changed.~1 changedView diff

Install

Pinned to version 0.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http growvib https://api.growvib.com/mcp-public
claude mcp add --transport http growvib https://api.growvib.com/mcp-public

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__growvib__get_checkout_status",
      "mcp__growvib__get_paid_order_status",
      "mcp__growvib__get_quote",
      "mcp__growvib__get_service",
      "mcp__growvib__list_paid_orders"
    ],
    "ask": [
      "mcp__growvib__create_checkout",
      "mcp__growvib__recommend_service",
      "mcp__growvib__search_catalog"
    ],
    "deny": [
      "mcp__growvib__create_paid_order"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as growvib. Review it before you use it.

Capability tags behind 2 rules
  • mcp__growvib__create_checkout untrusted-input
  • mcp__growvib__create_paid_order untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.growvib/growvib/verify?hash=c1ac8ad73cdf730b84b15ce6c5dd1c4cbb74a71c44158054368b18b1fb9a6d46" | jq -e '.changed == false'

Pinned hash c1ac8ad73cdf, from Nov 21, 2026, 03:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.growvib/growvib/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.growvib/growvib
[![Anlyon Radar](https://radar.anlyon.com/badge/com.growvib/growvib.svg)](https://radar.anlyon.com/servers/com.growvib/growvib)

Source: MCP Registry. Synced Nov 7, 2026, 00:17 UTC.

GrowVib: Social Media Growth MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the GrowVib: Social Media Growth MCP server safe?

No scan can promise that. What its definitions show: 9 tools, 4 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the GrowVib: Social Media Growth MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: create_paid_order.

Can the GrowVib: Social Media Growth MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the GrowVib: Social Media Growth MCP server have?

9 tools: 1 destructive, 3 write, 5 read. create_paid_order, create_checkout, recommend_service, search_catalog, get_checkout_status, get_paid_order_status, get_quote, get_service and 1 more.

Does the GrowVib: Social Media Growth MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the GrowVib: Social Media Growth MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the GrowVib: Social Media Growth MCP server changed its tools?

Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.