# Loop Marketing (remote · loopmarket.ing)

Read Apple, Google, Meta and TikTok ad campaigns and draft changes a person approves in Loop.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `loopmarket.ing`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ing-loopmarket-loop/api-mcp.md), [page](https://verifymcp.io/servers/ing-loopmarket-loop/api-mcp)

## Channel facts

- Endpoint: `https://loopmarket.ing/api/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 51/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2335 tokens (~233/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Loop Marketing MCP server?

Loop Marketing is a hosted endpoint at https://loopmarket.ing/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ing-loopmarket-loop 'https://loopmarket.ing/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ing-loopmarket-loop": {
      "url": "https://loopmarket.ing/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ing-loopmarket-loop": {
      "type": "http",
      "url": "https://loopmarket.ing/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ing-loopmarket-loop]
url = "https://loopmarket.ing/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ing-loopmarket-loop": {
      "type": "remote",
      "url": "https://loopmarket.ing/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ing-loopmarket-loop --url 'https://loopmarket.ing/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ing-loopmarket-loop:
    url: "https://loopmarket.ing/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ing-loopmarket-loop": {
      "Transport": "http",
      "Url": "https://loopmarket.ing/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ing-loopmarket-loop -t streamable-http -u 'https://loopmarket.ing/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ing-loopmarket-loop": {
      "type": "http",
      "url": "https://loopmarket.ing/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-20 (score 76, 0)

- [security] Tool “prepare_campaign_change” rewrote its description, which is the text the model reads
- [cosmetic] “create_launch_draft” added an optional parameter “deviceOs”

### 2026-11-19 (score 76, +1)

- [security] Tool “prepare_campaign_change” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 203 → 228
- [cosmetic] “create_launch_draft” added an optional parameter “ageMax”
- [cosmetic] “prepare_campaign_change” added an optional parameter “ageMax”
- [cosmetic] “prepare_campaign_change” added an optional parameter “event”
- [cosmetic] “prepare_campaign_change” added an optional parameter “instagramPositions”

### 2026-11-18 (score 75, 0)

- [security] Tool “prepare_campaign_change” rewrote its description, which is the text the model reads
- [cosmetic] “create_launch_draft” added an optional parameter “ageMin”
- [cosmetic] “prepare_campaign_change” added an optional parameter “ageMin”
- [cosmetic] “prepare_campaign_change” reworded the description of “amount”
- [cosmetic] “prepare_campaign_change” reworded the description of “campaignId”
- [cosmetic] “prepare_campaign_change” reworded the description of “fromCampaignId”

### 2026-11-16 (score 75, +1)

- [security] Tool “prepare_campaign_change” rewrote its description, which is the text the model reads
- [cosmetic] “prepare_campaign_change” added an optional parameter “newKeywords”
- [cosmetic] “prepare_campaign_change” reworded the description of “adGroupName”
- [cosmetic] “prepare_campaign_change” reworded the description of “bid”
- [cosmetic] “prepare_campaign_change” reworded the description of “matchType”
- [cosmetic] “prepare_campaign_change” reworded the description of “overrideWorkspaceCap”

### 2026-11-15 (score 74, 0)

- [security] Tool “list_campaigns” rewrote its description, which is the text the model reads
- [security] Tool “prepare_campaign_change” rewrote its description, which is the text the model reads
- [cosmetic] “prepare_campaign_change” reworded the description of “adGroupName”
- [cosmetic] “prepare_campaign_change” reworded the description of “maxCpc”

### 2026-11-14 (score 74, 0)

- [security] Tool “prepare_campaign_change” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1522 → 1713
- [functional] New tool “get_spend_audit”
- [cosmetic] “prepare_campaign_change” added an optional parameter “bid”
- [cosmetic] “prepare_campaign_change” added an optional parameter “keyword”
- [cosmetic] “prepare_campaign_change” added an optional parameter “matchType”
- [cosmetic] “prepare_campaign_change” reworded the description of “adGroupName”

### 2026-11-13 (score 74, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03

## MCP tools (10)

### `list_workspaces` (~30 tokens)

List workspaces

The workspace this API key belongs to (one per key), with its currency and the key's scope.

### `get_overview` (~56 tokens)

Workspace overview

Home KPIs (spend, paid installs, cost per install vs the previous period), the honest headline, measurement caveats and how many proposals wait for a person.

Input parameters:

- `window` (integer): Days. Default follows the data.

### `list_campaigns` (~46 tokens)

List campaigns

Campaigns this workspace manages, with state, budget and platform-reported spend, installs and (where the channel reports them) purchases in the window.

Input parameters:

- `window` (integer)

### `get_spend_audit` (~82 tokens)

Audit ad spend

A spend check over the window: campaigns to stop (spend that did not turn into purchases or installs at a cost the workspace can afford), campaigns worth more budget, campaigns with spend but no purchase yet, and ones without enough results to judge. Uses the same verdicts as the Campaigns page and changes nothing.

Input parameters:

- `window` (integer)

### `get_campaign` (~47 tokens)

Get campaign

One campaign by id (from list_campaigns): numbers, daily spend, pending proposals and what was executed on it.

Input parameters:

- `campaignId` (string, required)
- `window` (integer)

### `list_proposals` (~58 tokens)

List proposals

The inbox: proposals waiting for a person, ones a guardrail is holding, and the recent execution log (newest first) with each failure's message.

Input parameters:

- `limit` (integer): Max rows of the execution log. Default 20.

### `create_launch_draft` (~545 tokens)

Create launch draft

Prepare a new campaign as a proposal in the Loop inbox (needs a propose key). Same checks as the Loop form: connected channel, unique name, budget plan, guardrails. Nothing is sent to the ad platform; a person approves it in Loop.

Input parameters:

- `ageMax` (integer): Meta only: oldest age the ad is shown to, as a hard limit (turns Advantage+ audience off). Omit for no limit.
- `ageMin` (integer): Meta only: youngest age the ad is shown to. Omit for no limit.
- `amount` (number, required): Total budget in major units of the currency the channel's ad account bills in (e.g. 30000 for ¥30,000). Channels whose account currency cannot be read use the workspace currency.
- `amountCurrency` (string): The currency you mean the amount in (ISO 4217, e.g. JPY). If the ad account bills in another currency, nothing is saved.
- `appEvent` (string): Meta app event to optimise for instead of installs (see list_app_events).
- `bodyText` (string)
- `channel` (string, required): Ad platform key, e.g. meta, google_ads, tiktok, apple_search_ads, microsoft_ads, linkedin_ads, amazon_ads. Must be connected.
- `countries` (array): ISO country codes, e.g. ["JP"].
- `deviceOs` (string): Meta only: show the ad only on this device OS, as a hard limit (turns Advantage+ audience off). Omit for every device.
- `draftId` (string): Id of a pending draft to replace. Omit for a new draft.
- `endTime` (string, required): End, ISO 8601 with offset, e.g. 2026-11-30T23:59:59+09:00.
- `headline` (string)
- `imageCreativeId` (string): Creative id from this workspace.
- `libraryAssetId` (string): Library file id from this workspace.
- `link` (string): Destination URL (store or website).
- `moreHeadlines` (array): Google Ads App campaigns only: the 2nd to 5th headlines (Google needs 2–5, each up to 30 wide; full-width counts as 2).
- `name` (string, required): Campaign name. Must not exist in the workspace or wait in the inbox already.
- `placements` (array): Meta placements. Omit to let Meta choose.
- `startTime` (string): Optional start, ISO 8601 with offset.
- `youtubeVideoIds` (array)

### `prepare_campaign_change` (~1307 tokens)

Prepare a change to a campaign

Prepare a change to an existing campaign as a proposal in the Loop inbox (needs a propose key): set a Google Ads search campaign's languages, replace a running search ad's wording and landing page, change a daily budget by more than the per-change limit (the daily cap still applies), give a campaign a total cap that Loop pauses it at, set a max CPC you choose (campaign or ad group; above the workspace max CPC only with overrideWorkspaceCap), move the same daily amount from one campaign to another (total unchanged; both or neither), add an ad group (keywords and one responsive search ad) to a running Google Ads search campaign within its current budget, move a Google Ads or Apple Ads campaign's end date (optionally raising the total cap Loop watches so it does not pause before the new end), keep only chosen keywords in an Apple Ads campaign and pause the rest, set the bid of one keyword in an Apple Ads campaign (daily budget unchanged), add keywords (exact match by default) at one bid to an Apple Ads ad group (daily budget unchanged), set the default bid of an Apple Ads ad group with max_cpc and adGroupName (what a Search Match ad group with no keywords bids), pause a running or scheduled campaign with pause_campaign (budget, end date and ads unchanged; needs only campaignId), set the youngest age a Meta campaign's ad sets or an Apple Ads campaign's ad groups are shown to with min_age and ageMin, optionally (Meta only) with ageMax for the oldest age (Advantage+ audience is turned off so the range is a hard limit; budget, placements and ads unchanged), narrow the Instagram placements of a Meta campaign whose ad sets run on Instagram only with placements and instagramPositions, e.g. ["stream", "reels"] to drop Stories (narrowing only; budget, ages and ads unchanged), change the pixel event a Meta website campaign's ad sets optimize for with optimization_event and event (pixel, budget, targeting and ads unchanged; Meta restarts learning, so a person always approves it)…

Input parameters:

- `adGroupName` (string): max_cpc: an ad group of a manual CPC campaign (omit for the campaign max CPC); on Apple Ads the ad group whose default bid changes (may be omitted when the campaign has one ad group). add_ad_group: t…
- `adRef` (string): replace_search_ad: the ad to replace (customers/…/adGroupAds/…).
- `ageMax` (integer): min_age: optional oldest age (at least ageMin). Turns off Advantage+ audience so Meta keeps the range as a hard limit.
- `ageMin` (integer): min_age: the youngest age the campaign's ad sets are shown to.
- `amount` (number): budget_transfer: the daily amount to move. total_transfer: the amount of total budget to move.
- `bid` (number): keyword_bid: the new max bid in the account's currency (major units, e.g. 376 for ¥376). add_keywords: the new keywords' max bid.
- `campaignId` (string, required): The campaign id from list_campaigns (budget_transfer, total_transfer: the campaign that receives).
- `cap` (number): total_cap: the total in the campaign's currency.
- `dailyBudget` (number): budget_move: the new daily budget in the campaign's currency.
- `descriptions` (array)
- `endDate` (string): end_date: the new last day (YYYY-MM-DD) in the ad account's time zone.
- `event` (string): optimization_event: Meta's custom_event_type to optimize for (CONTENT_VIEW = ViewContent, START_TRIAL = StartTrial, …).
- `family` (string): replace_search_ad / add_ad_group: the workspace campaign family for utm_campaign.
- `fromCampaignId` (string): budget_transfer, total_transfer: the campaign that gives the budget.
- `fundedBy` (string): budget_move: id of the campaign whose budget this uses (recorded only).
- `headlines` (array)
- `instagramPositions` (array): placements: the Instagram positions to keep (stream = Feed, story = Stories, reels, explore, …). Must be fewer than the ad sets use now.
- `keep` (array): keep_keywords: the keyword texts to keep enabled; the campaign's other enabled keywords are paused.
- `keyword` (string): keyword_bid: the text of the enabled keyword whose bid changes.
- `keywords` (array): add_ad_group: the new ad group's keywords.
- `kind` (string, required)
- `landing` (string): replace_search_ad / add_ad_group: landing page without utm_*; UTM is added by Loop.
- `languages` (array): languages: codes such as vi, ja; empty = all languages.
- `matchType` (string): keyword_bid: only needed when the same text is enabled with more than one match type. add_keywords: the match type (default EXACT).
- `maxCpc` (number): max_cpc: the new max CPC in the account's currency (Apple Ads: the ad group's default bid). add_ad_group: the new ad group's max CPC (manual CPC campaigns only).
- `newKeywords` (array): add_keywords: the keyword texts to add (up to 20); each gets matchType (default EXACT) and bid.
- `overrideWorkspaceCap` (boolean): max_cpc / add_keywords: allow a bid above the workspace max CPC.
- `raiseTotalCap` (boolean): end_date: if Loop watches a total cap on this campaign, raise it by the added days × daily budget.
- `since` (string): total_cap: YYYY-MM-DD to count spend from (default today).
- `utmCampaign` (string): replace_search_ad / add_ad_group: utm_campaign for this campaign ({adgroup} allowed).

### `list_app_events` (~29 tokens)

List app events

Meta in-app events this workspace's app sends, usable as appEvent in create_launch_draft.

### `list_budget_tests` (~29 tokens)

List budget tests

Guardrailed budget tests: campaign, dates, daily range, stop rules and the latest verdict.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ing-loopmarket-loop/api-mcp#diagnostics

## Score history

- 2026-11-21: 77
- 2026-11-20: 76
- 2026-11-19: 76
- 2026-11-18: 75
- 2026-11-17: 75
- 2026-11-16: 75
- 2026-11-15: 74
- 2026-11-14: 74
- 2026-11-13: 74
- 2026-11-12: 73

## Common questions

### What is the Loop Marketing MCP server?

Loop Marketing is an MCP server listed in the public MCP registry as ing.loopmarket/loop. Read Apple, Google, Meta and TikTok ad campaigns and draft changes a person approves in Loop. This page covers its hosted endpoint (https://loopmarket.ing/api/mcp).

### Is the Loop Marketing MCP server safe to use?

Loop Marketing scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Loop Marketing MCP server expose?

Loop Marketing exposes 10 tools: list_workspaces, get_overview, list_campaigns, get_spend_audit, get_campaign, and 5 more. Their descriptions and schemas cost roughly 2,229 tokens of context every time the server is loaded.

### Does the Loop Marketing MCP server require authentication?

Yes. Loop Marketing asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Loop Marketing MCP server still maintained?

Loop Marketing is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Loop Marketing MCP server?

VerifyMCP ran 13 checks on Loop Marketing, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://loopmarket.ing/api/mcp
- Authorisation metadata: https://loopmarket.ing/.well-known/oauth-protected-resource/api/mcp
- Website: https://loopmarket.ing/guides/ad-accounts-mcp?src=mcp-dir
- Changelog RSS feed: https://verifymcp.io/servers/ing-loopmarket-loop/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ing-loopmarket-loop/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ing-loopmarket-loop/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ing-loopmarket-loop/api-mcp
