Skip to main content
Ask your agent this, with <product-name> replaced by your product’s name:
The agent reads your analytics, prompts, content, and knowledge files, suggests changes, and makes the ones you approve.

Before you ask

  • Connect the server and sign in. See Connect the MCP server.
  • If you belong to more than one organization, put your organization slug in the same message. See Find your organization slug.
  • Use the product name as it appears in TPC.
  • Decide how far the agent may go, for example drafts only, or drafts and publishing.
  • Generating content drafts needs an active or trial Pro or Enterprise subscription.

What the agent does

The agent chooses its own calls. A typical run follows these steps.
1

Find the product

list_organizations finds your organization slug if you did not give it. list_products returns the product’s slug and ID, and get_product returns its description, keywords, differentiators, competitors, and product context.
2

Find the gaps

explore_analytics with metric: "sov", dimension: "prompt", sortBy: "sov", and sortDirection: "asc" lists your tracked prompts from the lowest share of voice up. With dimension set to topic or competitor, it shows where you are weak and who ranks above you. With metric: "citations", dimension: "source", and filters.productMentioned: "not_mentioned", it shows which sources answer engines cite when they leave your product out. list_prompts shows the prompts TPC tracks.
3

Check what exists

list_content lists your live pages, or drafts in review when the agent sets status. get_content reads one page or draft in full. list_knowledge_files and get_knowledge_file read the product’s knowledge files. list_prompt_suggestions lists candidate prompts that are not tracked yet.
4

Propose and make changes

The agent proposes changes. After you approve them, it runs the write tools below.
5

Measure again

After the next prompt runs, the agent can repeat the same explore_analytics queries to see whether share of voice moved on those prompts.
The server tells the agent to write drafts for your lowest share-of-voice prompts with generate_content_drafts and their prompt IDs, so each draft stays linked to the prompt it targets. It uses create_content_draft only for text you already wrote. You can also say which prompts to write for, for example: “Generate drafts for my five lowest share-of-voice prompts.”

Write tools

Approval

Your MCP client asks for your approval before it runs a write tool, unless you have allowed that tool to run without asking. The server marks each write tool as one that changes data. Its instructions also tell the agent to confirm with you first. That covers creating, updating, or deleting anything, writing a knowledge file, and approving prompt suggestions.
Read these before you approve:
  • Deleting a draft in review with delete_content is permanent. You cannot restore it.
  • delete_prompt archives a prompt. It cannot permanently delete one.
  • Approving prompt suggestions adds tracked prompts and may change future share of voice results.
If a write tool times out, the change may still have gone through. Ask the agent to check before it retries.

What you get back

  • The gaps the agent found and the changes it proposes
  • For each change you approve, the tool’s result, such as new draft IDs and titles, the new or changed prompt, the number of suggestions approved or rejected, or the commit for a knowledge file
  • New drafts, which stay in review until you approve them. Generated drafts reach pending_review when generation finishes. You can also review drafts in TPC. See Create content.