Koskamo

Campaign Pack MCP

An official MCP server that allows AI agents to generate full client-ready ad campaigns, including copy, images, music, and PDF deliverables, from a product photo and brief.

Visit Campaign Pack

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Campaign Pack MCP logo, by Campaign PackVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Campaign Pack
You need:You need a Campaign Pack account to connectCustom connectors need a paid Claude plan
MCP endpoint (Streamable HTTP)
https://tools.campaignpack.ai/mcp
Vendor documentation

What its tools do

9 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (3)

Can change data (6)

9 of 9 have a description · 9 of 9 declare behavior hints · 9 of 9 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to campaignpack.ai ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Generate story, emails, and ad copy
  • Create hero images and social crops
  • Produce audio beds and stings
  • Export client-ready PDF packs

Source and maintenance

Vendor evidenceRegistry 0.1.1
mcp-registry: ai.campaignpack/campaignpack@0.1.1Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
campaignpack 0.1.0
MCP protocol negotiated in check
2025-06-18
Tools
9 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Campaign Pack turns a product photo and a brief into a complete marketing campaign — plan, ideas, ad and social scripts, a creator brief, stills and a client-ready PDF. Everything runs on Campaign Pack's own GPUs; no third-party model provider ever sees the user's product. You write the brief. Interview the user about the product, the buyer and the positioning, then hand a specific, factual brief to start_campaign — it is the single biggest lever on how good the pack is. Never invent metrics, customers or prices. A run takes minutes, not seconds. start_campaign returns a job id immediately; poll check_campaign roughly every 20 seconds. There is one GPU, so runs serialise: never start a second campaign while one is going. A campaign is multiplayer. share_campaign lets a teammate open the same run from their own client while it is still going.

Tools

9 advertised

start_campaign — Start a campaign
Advertised by the server during the last successful anonymous check.
Open-world

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.

start_campaign input schema
{
  "type": "object",
  "required": [
    "brief",
    "brand"
  ],
  "properties": {
    "size": {
      "enum": [
        "text",
        "lite"
      ],
      "type": "string",
      "description": "Pack size. Available here: 'text' (about a minute), 'lite' (about ten minutes)."
    },
    "brand": {
      "type": "string",
      "description": "The brand name, spelled exactly as the customer spells it. Every mention in the pack is rewritten to match this."
    },
    "brief": {
      "type": "string",
      "description": "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": {
      "type": "string",
      "description": "Workspace path from upload_product_photo. Required for the image sizes: the stills are edited from the real photo rather than generated from nothing."
    }
  }
}
start_campaign annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
check_campaign — Check campaign progress
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

check_campaign input schema
{
  "type": "object",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "Job id returned by start_campaign."
    }
  }
}
check_campaign annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_pack — Get the finished pack
Advertised by the server during the last successful anonymous check.
Advertised read-only

Collect a finished campaign: the folder, its files, the written overview, and the path to the PDF.

get_pack input schema
{
  "type": "object",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "Job id returned by start_campaign."
    }
  }
}
get_pack annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
upload_product_photo — Upload a product photo
Advertised by the server during the last successful anonymous check.

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

upload_product_photo input schema
{
  "type": "object",
  "required": [
    "filename",
    "data_base64"
  ],
  "properties": {
    "filename": {
      "type": "string",
      "description": "Name to save it under, with the extension — 'bottle.jpg'. Reusing a name that is already there replaces that photo."
    },
    "data_base64": {
      "type": "string",
      "description": "The image file's bytes, base64-encoded. The raw image, not a data: URL and not a path on your own machine."
    }
  }
}
upload_product_photo annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
share_campaign — Share a campaign
Advertised by the server during the last successful anonymous check.

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.

share_campaign input schema
{
  "type": "object",
  "required": [
    "session_id",
    "email"
  ],
  "properties": {
    "email": {
      "type": "string",
      "description": "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": {
      "type": "string",
      "description": "Campaign to act on — the session id from start_campaign or check_campaign."
    }
  }
}
share_campaign annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_campaign_access — List who can see a campaign
Advertised by the server during the last successful anonymous check.
Advertised read-only

Who owns a campaign and who it is shared with.

list_campaign_access input schema
{
  "type": "object",
  "required": [
    "session_id"
  ],
  "properties": {
    "session_id": {
      "type": "string",
      "description": "Campaign to act on — the session id from start_campaign or check_campaign."
    }
  }
}
list_campaign_access annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
unshare_campaign — Remove someone's access
Advertised by the server during the last successful anonymous check.
Advertised destructive

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

unshare_campaign input schema
{
  "type": "object",
  "required": [
    "session_id",
    "email"
  ],
  "properties": {
    "email": {
      "type": "string",
      "description": "Email address of the collaborator to remove. The owner cannot be removed this way."
    },
    "session_id": {
      "type": "string",
      "description": "Campaign to act on — the session id from start_campaign or check_campaign."
    }
  }
}
unshare_campaign annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": true
}
answer_approval — Answer an approval prompt
Advertised by the server during the last successful anonymous check.
Open-world

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

answer_approval input schema
{
  "type": "object",
  "required": [
    "job_id",
    "decision"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "Job id returned by start_campaign."
    },
    "decision": {
      "enum": [
        "allow",
        "refuse"
      ],
      "type": "string",
      "description": "What the person said: 'allow' to let the run go ahead, 'refuse' to deny it. This must be their answer, not yours."
    }
  }
}
answer_approval annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
abort_campaign — Stop a campaign
Advertised by the server during the last successful anonymous check.
Advertised destructive

Stop a running campaign.

abort_campaign input schema
{
  "type": "object",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "Job id returned by start_campaign."
    }
  }
}
abort_campaign annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
172 ms
95th percentile latency
172 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 172 ms · metadata changed · 9 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http campaign-pack-mcp https://tools.campaignpack.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add campaign-pack-mcp --url https://tools.campaignpack.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable campaign-pack-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "campaign-pack-mcp": {
      "url": "https://tools.campaignpack.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "campaign-pack-mcp": {
      "type": "streamableHttp",
      "url": "https://tools.campaignpack.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start campaign-pack-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "campaign-pack-mcp": {
      "type": "http",
      "url": "https://tools.campaignpack.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http campaign-pack-mcp https://tools.campaignpack.ai/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://tools.campaignpack.ai/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "campaign-pack-mcp": {
      "serverUrl": "https://tools.campaignpack.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Campaign Pack MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 642

Do you run Campaign Pack MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing