# Campaign Pack (remote · tools.campaignpack.ai)

Turn a product photo and a brief into a full ad campaign: scripts, stills, client-ready PDF.

- Trust score: 83/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `tools.campaignpack.ai`: 83/100 (this document), [markdown](https://verifymcp.io/servers/ai-campaignpack-campaignpack/tools.md), [page](https://verifymcp.io/servers/ai-campaignpack-campaignpack/tools)

## Channel facts

- Endpoint: `https://tools.campaignpack.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.1.1`

## 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, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1484 tokens (~114/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Campaign Pack MCP server?

Campaign Pack is a hosted endpoint at https://tools.campaignpack.ai/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 ai-campaignpack-campaignpack 'https://tools.campaignpack.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-campaignpack-campaignpack": {
      "url": "https://tools.campaignpack.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-campaignpack-campaignpack": {
      "type": "http",
      "url": "https://tools.campaignpack.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-campaignpack-campaignpack]
url = "https://tools.campaignpack.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-campaignpack-campaignpack": {
      "type": "remote",
      "url": "https://tools.campaignpack.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-campaignpack-campaignpack --url 'https://tools.campaignpack.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-campaignpack-campaignpack:
    url: "https://tools.campaignpack.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-campaignpack-campaignpack": {
      "Transport": "http",
      "Url": "https://tools.campaignpack.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-campaignpack-campaignpack -t streamable-http -u 'https://tools.campaignpack.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-campaignpack-campaignpack": {
      "type": "http",
      "url": "https://tools.campaignpack.ai/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 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 80, 0)

- [security] Tool “get_pack” rewrote its description, which is the text the model reads
- [security] Tool “list_campaigns” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [cosmetic] “check_campaign” added an optional parameter “session_id”
- [cosmetic] “get_pack” added an optional parameter “session_id”
- [cosmetic] “check_campaign” made “job_id” optional
- [cosmetic] “get_pack” made “job_id” optional

### 2026-11-15 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-08 (score 77, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.1.0 → 0.1.1

## MCP tools (13)

### `start_campaign` (~246 tokens)

Start a campaign

Start a marketing campaign pack on Campaign Pack's own GPUs. Produces a campaign plan, ideas, ad and social scripts, a creator brief, and a client-ready PDF — plus product stills on the image sizes. Returns immediately with a job id; the run itself takes minutes, so poll check_campaign rather than waiting. Write the brief yourself from what the user told you: the richer and more specific it is, the better the pack. Nothing is sent to any third-party model provider.

Input parameters:

- `brand` (string, required): The brand name, spelled exactly as the customer spells it. Every mention in the pack is rewritten to match this.
- `brief` (string, required): What the product is, who it is for, what matters about it. A few sentences to a few paragraphs. State only facts the user gave you — invented metrics or customers end up in the finished pack.
- `photo` (string): Workspace path from upload_product_photo. Required for the image sizes: the stills are edited from the real photo rather than generated from nothing.
- `size` (string): Pack size. Available here: 'text' (about a minute), 'lite' (about ten minutes).

### `check_campaign` (~102 tokens)

Check campaign progress

Progress of a running campaign: status, the tools it has just called, queue position, and whether it is waiting for a human approval. Poll about every 20 seconds.

Input parameters:

- `job_id` (string): Job id returned by start_campaign.
- `session_id` (string): Campaign to follow, from list_campaigns. An alternative to job_id for a run started in another conversation; only works while it is still going. job_id wins when both are given.

### `get_pack` (~113 tokens)

Get the finished pack

Collect a finished campaign: the folder, its files, the written overview, and the path to the PDF. Takes the job_id from start_campaign, or the session_id from list_campaigns — use session_id for a campaign run in an earlier conversation, where no job id survives.

Input parameters:

- `job_id` (string): Job id returned by start_campaign.
- `session_id` (string): Campaign to collect, from list_campaigns. An alternative to job_id, not an addition: job_id wins when both are given.

### `list_campaigns` (~92 tokens)

List past campaigns

Campaigns on this account, newest first, including ones shared with it. Start here when you do not already have an id — the ids from start_campaign only exist in the conversation that made them, so this is how you find a campaign from last week. Pass a session_id from here to get_pack to open one.

Input parameters:

- `limit` (integer): How many to return, newest first. Default 20.

### `list_workspace_files` (~90 tokens)

List workspace files

List files and folders in the account's workspace — campaign folders, scripts, product stills, PDFs, uploads. Directories end in '/'.

Input parameters:

- `path` (string): Folder to list, relative to the workspace. Omit or '.' for the top level.
- `session_id` (string): Look inside a campaign shared with this account rather than its own files. Omit for your own workspace.

### `read_workspace_file` (~97 tokens)

Read a workspace file

Contents of a text file in the workspace — a script, the plan, the creator brief, a transcript. Large files are truncated. For a PDF, image or video call get_download_url instead.

Input parameters:

- `path` (string, required): File path relative to the workspace, as shown by list_workspace_files.
- `session_id` (string): Read from a campaign shared with this account rather than its own files. Omit for your own workspace.

### `get_download_url` (~108 tokens)

Get a download link

A link the person can open to get one file — the campaign PDF, a product still, a video. Works for any file in the workspace, including ones too big or too binary to read as text. The link expires within the hour.

Input parameters:

- `path` (string, required): File path relative to the workspace, as shown by list_workspace_files.
- `session_id` (string): Link a file from a campaign shared with this account rather than its own files. Omit for your own workspace.

### `upload_product_photo` (~106 tokens)

Upload a product photo

Put a product photo into the user's workspace so a campaign can edit stills from the real thing. Base64 of the image bytes.

Input parameters:

- `data_base64` (string, required): The image file's bytes, base64-encoded. The raw image, not a data: URL and not a path on your own machine.
- `filename` (string, required): Name to save it under, with the extension — 'bottle.jpg'. Reusing a name that is already there replaces that photo.

### `share_campaign` (~130 tokens)

Share a campaign

Give a teammate access to a campaign by email address — including while it is still running. They see the same live run from their own AI client or the website, can abort it, answer its approval prompts, and take the next turn. They must already have a Campaign Pack account; sharing does not create one.

Input parameters:

- `email` (string, required): Email address of the person to let in. They must already have a Campaign Pack account under this address; sharing does not create one or send an invitation.
- `session_id` (string, required): Campaign to act on — the session id from start_campaign or check_campaign.

### `list_campaign_access` (~42 tokens)

List who can see a campaign

Who owns a campaign and who it is shared with.

Input parameters:

- `session_id` (string, required): Campaign to act on — the session id from start_campaign or check_campaign.

### `unshare_campaign` (~67 tokens)

Remove someone's access

Revoke a collaborator's access. Takes effect on their next request.

Input parameters:

- `email` (string, required): Email address of the collaborator to remove. The owner cannot be removed this way.
- `session_id` (string, required): Campaign to act on — the session id from start_campaign or check_campaign.

### `answer_approval` (~86 tokens)

Answer an approval prompt

Answer a paused run that wants to send the user's data somewhere outside Campaign Pack. Ask the person; never decide for them.

Input parameters:

- `decision` (string, required): What the person said: 'allow' to let the run go ahead, 'refuse' to deny it. This must be their answer, not yours.
- `job_id` (string, required): Job id returned by start_campaign.

### `abort_campaign` (~27 tokens)

Stop a campaign

Stop a running campaign.

Input parameters:

- `job_id` (string, required): Job id returned by start_campaign.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-campaignpack-campaignpack/tools#diagnostics

## Score history

- 2026-11-21: 83
- 2026-11-20: 82
- 2026-11-19: 82
- 2026-11-18: 81
- 2026-11-17: 81
- 2026-11-16: 80
- 2026-11-15: 80
- 2026-11-14: 79
- 2026-11-13: 79
- 2026-11-12: 79
- 2026-11-11: 78
- 2026-11-10: 78
- 2026-11-09: 77
- 2026-11-08: 77
- 2026-11-07: 76

## Common questions

### What is the Campaign Pack MCP server?

Campaign Pack is an MCP server listed in the public MCP registry as ai.campaignpack/campaignpack. Turn a product photo and a brief into a full ad campaign: scripts, stills, client-ready PDF. This page covers its hosted endpoint (https://tools.campaignpack.ai/mcp).

### Is the Campaign Pack MCP server safe to use?

Campaign Pack scores 83 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 Campaign Pack MCP server expose?

Campaign Pack exposes 13 tools: start_campaign, check_campaign, get_pack, list_campaigns, list_workspace_files, and 8 more. Their descriptions and schemas cost roughly 1,306 tokens of context every time the server is loaded.

### Does the Campaign Pack MCP server require authentication?

Yes. Campaign Pack 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 Campaign Pack MCP server still maintained?

Campaign Pack 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 Campaign Pack MCP server?

VerifyMCP ran 13 checks on Campaign Pack, 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://tools.campaignpack.ai/mcp
- Repository: https://github.com/campaignpack/campaignpack-mcp
- Website: https://campaignpack.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-campaignpack-campaignpack/tools.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-campaignpack-campaignpack/tools/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-campaignpack-campaignpack/tools.json
- HTML version of this page: https://verifymcp.io/servers/ai-campaignpack-campaignpack/tools
