MCP use cases - rocketblue

Practical ways to automate AI visibility work with rocketblue MCP — digests, competitor monitoring, prompt hygiene, outreach, content pipelines, and more. Connect an assistant once, then ask it to run these workflows in natural language. Each use case lists the MCP tools involved so you can adapt the flow in Cursor, Claude, or any MCP client.

Weekly visibility digest

Goal: After each scheduled report, produce a short summary for Slack, email, or a Notion page. Ask the agent:

For brand BRAND_ID, get the latest run stats and top mentioned competitors.
Write a 5-bullet weekly digest: share of voice, biggest gains/losses vs prior run,
and one recommended action.

Tools: list_runs → get_run_stats (current + previous run) Goal: Flag when a competitor jumps in mention share on priority prompts or topics. Ask the agent:

Compare the last 4 runs for brand BRAND_ID. Highlight any competitor whose
topic-level mention share rose more than 5%. List the prompts where they appear.

Tools: list_runs → get_run_stats → get_run_results (only for flagged prompts)

Prompt portfolio hygiene

Goal: Keep the tracked prompt set aligned with real buyer questions and within quota. Ask the agent:

Check remaining prompt slots for brand BRAND_ID. Find prompts with zero brand
mentions across the latest run. Propose replacements that are neutral and
consideration-stage, then wait for my approval before deleting or creating.

Tools: get_brand_context (with include: ["topics"]) → get_run_results → delete_items / create_topics_and_prompts

Citation gap and outreach

Goal: See which sites LLMs cite for your category, find the ones that skip you, and work them. Ask the agent:

For brand BRAND_ID, list the most cited pages that don't mention us. Classify their
domains, mark the best 5 as opportunities with a note, and find a contact for each.

Tools: get_outreach_cited_urls → update_outreach → get_outreach_contacts

AEO keyword mining from model search queries

Goal: Turn the queries models actually searched into a content and SEO backlog. Ask the agent:

Pull web search queries for brand BRAND_ID (ChatGPT and Perplexity only).
Cluster them into themes and output a prioritized brief list of article titles.

Tools: get_web_search_queries (with llmNames) → optionally get_content_suggestions

Content pipeline from gap to published post

Goal: Go from a missing prompt to a published article. Ask the agent:

List content suggestions from the latest run for brand BRAND_ID. Pick the top one,
write a draft, add a featured image and schema, and publish it to WordPress as a draft.

Tools: get_content_suggestions → create_content_draft → get_created_content → generate_content_assets → publish_content Drafts and images use credits. The agent should confirm the cost first.

Page and site audits

Goal: Find what keeps a page from being cited, then track it. Ask the agent:

Grade https://example.com/pricing for AI readiness and list the top fixes.
Then add the page to the content tracker for brand BRAND_ID.

Tools: analyze_website (mode: "page") → add_tracked_urls

Perception score tracking

Goal: Monitor branded perception properties (trust, clarity, etc.) over time. Ask the agent:

Export perception responses for brand BRAND_ID for the latest run and the
run before it. Table the score changes and quote one representative LLM explanation
per property that dropped.

Tools: list_runs → get_perception_results (×2). To change how later responses are scored, call update_perception_prompts. To fix a wrong score, call correct_results.

Agency multi-brand rollup

Goal: One assistant pass across every brand in the org for leadership reporting. Ask the agent:

List all brands. For each, pull brand context and latest run stats.
Produce a table: brand, prompt slots remaining, last run date, main-brand mention rate,
top competitor. Flag brands with no run in 14+ days.

Tools: get_organization_context → get_brand_context + get_run_stats per brand. Agency plans can follow up with generate_visibility_report.

Seed prompts from a research brief

Goal: Turn a GTM or category brief into a tracked topic and prompt set. Ask the agent:

Read this brief: [...]. Using get_usage_guide rules, propose topics and neutral
prompts for brand BRAND_ID. Check quota first. After I approve, create them.

Tools: get_usage_guide → get_brand_context → create_topics_and_prompts

Tips for reliable automation

Always start with get_organization_context and get_brand_context so the agent knows plan limits, credits, and schedule.
Pass brandId instead of runId to read the latest run without an extra call.
Prefer get_run_stats for dashboards; use includeAnswer: true only when you need raw model text.
New prompts are queued right away, but full reports follow the schedule. Digests should wait for a completed run.
For bulk cleanup, call delete_items once with all IDs.
Viewer and guest roles cannot connect MCP.

Connect an MCP client

Wire up Claude or Cursor.

Tools reference

Full tool catalog and costs.

Best practices

Quotas, prompt style, and session flow.

REST API

Same data over HTTP for scripts and backends.

​Weekly visibility digest

​Competitor share-of-voice watch

​Prompt portfolio hygiene

​Citation gap and outreach

​AEO keyword mining from model search queries

​Content pipeline from gap to published post

​Page and site audits

​Perception score tracking

​Agency multi-brand rollup

​Seed prompts from a research brief

​Tips for reliable automation

​Related