MCP Prompt Library

Create a line graph for the visibility of tracked term [BRAND NAME] in project [PROJECT NAME] from [DATE] to [DATE]. Show this per LLM active during this period so we can easily compare performance per LLM.

For project [PROJECT NAME], render a heatmap where the X-axis shows LLMs and the Y-axis shows brand terms, sorted by overall visibility descending. Color cells on a single-ramp scale (light → dark = low → high visibility %), and show the percentage value inside each cell. Goal: instantly see which brand dominates which LLM.

For project [PROJECT NAME], render a heatmap where the X-axis shows LLMs and the Y-axis shows brand terms, sorted by overall visibility descending. Color cells on a single-ramp scale (light → dark = low → high visibility %), and show the percentage value inside each cell. Goal: instantly see which brand dominates which LLM. Do this for the tag ‘TAG NAME’.

Use the Rankshift MCP and tell me: how does [your brand] show up in AI search right now — visibility score, mentions, and sentiment?

Find the tracked terms in project [PROJECT NAME] that had the biggest increase in visibility between [START DATE] and [END DATE]. Show the tracked term, starting visibility, ending visibility, and percentage-point change. Sort by the largest increase.

Find the tracked terms in project [PROJECT NAME] that experienced the largest decrease in visibility between [START DATE] and [END DATE]. Show the tracked term, previous visibility, current visibility, and percentage-point change. Sort by the largest decrease.

Identify the LLMs, tags, and prompts where [BRAND NAME] has its highest visibility in project [PROJECT NAME]. Show the top 10 opportunities where the brand is already performing strongly.

For [BRAND NAME] in project [PROJECT NAME], identify prompts where visibility has consistently increased or decreased over the last [NUMBER] days. Show the prompt, starting visibility, ending visibility, and overall change.

Create a line graph for the citation rate of tracked term [BRAND NAME] in project [PROJECT NAME] from [DATE] to [DATE]. Show this per LLM active during this period so we can easily compare performance per LLM.

Create a line graph for the citation rate of tracked term [BRAND NAME] in project [PROJECT NAME]. Show results for ChatGPT and overlay a 30-day moving average to highlight trend momentum and reduce noise.

Create a line graph showing the difference between tracked term [BRAND NAME] and [BRAND NAME] citation rate for ChatGPT over time. Goal: measure distance to the leader. Do this for the tag ‘TAG NAME’.

Create separate mini line charts for each active LLM using the same Y-axis scale. Goal: make pattern comparison easier without overlapping lines. Do this for tracked terms [BRAND NAME] and [BRAND NAME].

Use the Rankshift MCP and tell me which pages and domains get cited most often when AI answers mention us. Break it down by source and show me the trend over the last month.

Find the top 10 prompts in project [PROJECT NAME] where [BRAND NAME] has the highest visibility during [START DATE] to [END DATE]. Show the prompt, visibility rate, LLM, and tag where available. Sort from highest to lowest visibility.

Find the 10 prompts in project [PROJECT NAME] where [BRAND NAME] has the lowest visibility during [START DATE] to [END DATE]. Show the prompt, visibility rate, LLM, and tag where available. Sort from lowest to highest visibility.

Compare the most frequently cited source domains associated with [BRAND NAME] and [COMPETITOR NAME] in project [PROJECT NAME]. Show which domains are most commonly associated with each brand and identify differences in their citation sources.

Analyze the visibility of [BRAND NAME] in project [PROJECT NAME] over the last [NUMBER] days and identify unusual increases or decreases compared with the recent trend. For each anomaly, show the date, LLM, tracked term, previous visibility, and current visibility.

Pull all prompts in the project [PROJECT NAME] with the tag [TAG NAME] where the tracked term [BRAND NAME] has a visibility score of 0% (meaning [BRAND NAME] was not mentioned in the response).

For each of these prompts, return:

- The prompt text
- [BRAND NAME] visibility %
- Visibility % for [COMPETITOR 1]
- Visibility % for [COMPETITOR 2]

Sort the results by the highest competitor visibility score, so I can quickly identify prompts where competitors are performing well while [BRAND NAME] is absent.

Identify all prompts in project [PROJECT NAME] where my average visibility score was below 10% over the last 14 days.

For each identified prompt:

- Retrieve the top 5 most frequently cited URLs associated with that prompt during the same period.
- Analyze these URLs and identify the content type (blog article, comparison page, product page, guide, FAQ, landing page, directory, research page, etc.)
- Based on this analysis, recommend the single best content asset I should create to increase my chances of being cited in AI responses.

For each prompt, provide:

- Prompt text
- Current average visibility %
- Top 5 cited URLs
- Page title per URL

Use the Rankshift MCP and, based on our current AI visibility gaps, tell me the top 5 topics we should write about next. Also flag any existing pages that are thin or overlapping and could be merged.

Use the Rankshift MCP and pull the query fan-outs for our top prompts, then cross-reference them against our sitemap. Which topics do the models explore that we don't have a page for?

Identify the LLMs, tags, and prompts where [COMPETITOR NAME] has significantly higher visibility than [BRAND NAME]. Show the largest visibility gaps and the associated prompts.

Find all prompts in project [PROJECT NAME] where [BRAND NAME] has 0% visibility for at least one active LLM during [START DATE] to [END DATE]. Show the prompt, LLM, and visibility of [BRAND NAME] and the specified competitors.