MCP Servers

​

What is MCP?

​

GooseWorks MCP server

MCP vs CLI. The GooseWorks MCP and the GooseWorks CLI are two different things with different uses:

• The MCP gives your coding agent tools for your files, chat history, automations, and the Ad Remixer. It also exposes the GooseWorks skill catalog on demand through search_skills and fetch_skill, including the goose-ads and goose-video entry recipes. It does not install skill files on your machine.
• The CLI installs local GooseWorks skill files and can register the same MCP connection for your coding agent.

You can use the MCP without local skill files, or install both. npx gooseworks install --mcp (or --all) is a convenience that installs the CLI skills and registers this MCP server in one command. See CLI.

​

GooseWorks MCP — gooseworks

• URL: https://mcp.gooseworks.ai/mcp
• Transport: HTTP (streamable)
• Auth: Authorization: Bearer <your-api-key>

​

Files

• list_accessible_scopes — list every workspace you can reach
• list_directory — browse a workspace one level deep
• read_file — fetch a file inline (up to 10MB; binary returned as base64)
• write_file — create or overwrite a file via JSON (up to 50MB)
• get_upload_url / get_download_url — presigned S3 URLs for large or binary payloads
• get_ad_upload_url — presigned upload URL for a file that belongs to an ad project (a locally rendered video, its thumbnail, or a review ingredient). Use this instead of get_upload_url for ad-project files — it stores them in your organization’s shared Ads agent workspace, which is exactly where the Ad Remixer app reads them from, so the finished video always shows up in the app
• delete_file — remove a file or directory recursively
• search_files — find files by path substring

​

Chat history

• search_chat_history — search across chat sessions by keyword
• list_chat_sessions — list recent chat sessions for an agent
• get_chat_transcript — fetch the full message transcript for a session

​

Automations

• list_automations / get_automation — inspect existing automations
• create_automation — schedule a recurring job, or wire up an inbound webhook or email trigger
• update_automation — change the cron schedule, trigger config, or the agent instructions
• set_automation_enabled — pause or resume without deleting
• delete_automation — remove it

​

Ad Remixer

• list_ad_brands / get_brand_kit — read your brands and their kits
• search_ad_templates / surprise_me_templates — search or auto-pick a starting ad from the Community gallery
• estimate_remix_batch — preview the credit cost before spending
• submit_remix_batch / get_remix_batch — generate creatives and poll them to completion
• regenerate_creative — edit or re-roll a single creative

​

Skill catalog

• search_skills — discover matching GooseWorks skills.
• fetch_skill — load a skill’s complete instructions and bundled files.
• fetch_skill("goose-ads") — static ads, brand research, and campaign analysis.
• fetch_skill("goose-video") — video-ad projects and local final rendering.

​

Installing via the CLI

# GooseWorks MCP
npx gooseworks install --cursor --mcp

# Everything, all detected agents
npx gooseworks install --all

​

Manual setup (without the CLI)

​

Step 1 — Create an API token

1. Go to app.gooseworks.ai/settings?tab=coding_agents (Settings → Coding Agents).
2. Open the Manual MCP config tab and click Create MCP Token. This creates a user-scoped token with the mcp:access scope.
3. Copy the token (starts with cal_...) immediately — it’s shown once.

​

Step 2 — Add to your MCP client

{
  "mcpServers": {
    "gooseworks": {
      "type": "http",
      "url": "https://mcp.gooseworks.ai/mcp",
      "headers": {
        "Authorization": "Bearer cal_YOUR_TOKEN"
      }
    }
  }
}

{
  "mcpServers": {
    "gooseworks": {
      "type": "http",
      "url": "https://mcp.gooseworks.ai/mcp",
      "headers": {
        "Authorization": "Bearer cal_YOUR_TOKEN"
      }
    }
  }
}

​

Step 3 — Restart your editor

​

Rotating or revoking

• Rotate: create a new token, update mcp.json, revoke the old one in the UI.
• Revoke: Settings → Coding Agents → Your tokens → trash icon next to the token. Revocation is immediate — all active MCP sessions using that token will fail on their next request.

​

Adding your own custom MCP servers

1. Go to Settings > MCP Servers.
2. Click Add Server.
3. Enter the server URL and transport type (HTTP, SSE, or stdio).
4. Goose will discover the available tools automatically.

​

One-click integrations

• Notion
• GitHub
• Linear
• Google Docs
• Google Sheets
• Jira
• Confluence
• Gmail
• Slack