MCP Use Cases & Workflows

Access

MCP access is available on the Pro and Scale plans. See the MCP overview for setup.

Everything on this page is a real prompt you can type into a connected AI assistant. Single tools answer single questions; the real power is in compositions — the assistant chains tools together to run the workflows an SEO team actually runs.

Last updated: 2026-10-12

How writes work

When you ask your assistant to generate a brief or draft, Floyi’s own generation pipeline does the work — the exact same process as clicking Generate in the app. The result lands in your workspace with correct sections, internal links, and map position, and the assistant reads it back to you.

---

Getting Oriented

“What brands do I have and where do they stand?”

Ask	What happens
“List all my Floyi brands”	Every brand with summary stats
“Tell me everything about [brand]”	Full context: strategy, map summary, authority scores, pipeline health
“What’s the brand voice for [brand]?”	Reads the brand context resource
“Compare the authority scores of my two brands”	Side-by-side comparison
“How many credits do I have left?”	Balance across all pools, plus plan

Good for starting a planning session, briefing a new team member, or checking which brand needs attention.

Finding Opportunities

“Where am I weak and what should I write next?”

Ask	What happens
“Find the biggest content gaps for [brand]”	Gaps ranked across the map: missing content, weak coverage, low rankings
“Find gaps in the ‘[cluster]’ cluster”	Scoped to one part of the map
“Run a gap analysis for [brand]”	Prioritized gap report (built-in prompt)
“Audit which topics have briefs and articles”	Authoritative per-node content audit, split by content topics vs. site pages (built-in prompt)
“Analyze the Organic Audit report to find our best opportunities”	Reads connected Search Console data against the map: pages and queries gaining or losing, mapped to topics
“What silos are we growing fastest in according to the Organic Audit?”	Pillar-level trend from GSC performance, so investment follows momentum
“Which topics should we brief and draft next to complete topical coverage?”	Ranks the map’s uncovered topics by what closes a pillar fastest, not by volume
“Generate a weekly report for [brand]”	Pipeline status, top gaps, and progress in one summary
“Search for topics about ‘[keyword]’ in my map”	Existing topics with content status — check before you write
“What’s the search intent and funnel stage of [topic]?”	The values shown in the Planner, including whether you set them by hand
“List the BOFU topics in [brand] that still need content”	Topics filtered by the Planner’s funnel stage, joined with content status

Three gap types come back: missing (no published content), weak coverage (content exists but covers the topic thinly), and low ranking (published but ranking past position 20). Missing is your net-new queue; the other two are your refresh queue.

Generating Briefs & Drafts

“Create a brief for this topic, then draft it.”

Brief generation mirrors the app’s four-step modal: competitors, personas, keywords + knowledge base, then links. The last three inputs are optional at the API level, but the assistant should walk through every step and only skip one when you explicitly choose to:

Ask	What happens
“Get the SERP data for [topic] — how old is it?”	Stored SERP results with age, so you can decide whether to refresh
“That’s stale — fetch fresh SERP data”	New results, saved to the same storage the app uses. Uses credits, charged only when the fetch succeeds
“Brief this topic using results 1, 2, 4, and 6”	The assistant selects competitors the way you would with checkboxes
“Use persona [name] and pull in the knowledge base”	Personas and KB scope included in the brief
“Is my brief done yet?”	Progress check
“Generate a draft from the completed brief”	Floyi drafts it natively
“Show me the full draft”	Reads the current MCP-readable text section by section; if the latest content exists only in the rich-text editor, the assistant tells you to review it in the app
“Which AI models can I use and what do they cost?”	Models with credit multipliers — choose a lower-cost model for this run if needed
“What terms should the draft for brief [id] cover?”	Content Optimizer terms and entities, ranked by relevance
“Replace the weak competitor-comparison section in this brief”	Free, versioned brief curation without regenerating the whole brief
“Use the Research Agent and add an intro with key takeaways”	Enables the draft specialists before generation; specialist costs are included in the estimate
“Fix the inaccurate claim in section 4”	Targeted plain-text section edit, provided the article is not open in the app editor
“Re-score the draft after that fix”	Runs the Page Quality Scorecard again for 10 credits, charged only if the run succeeds

Briefs for map topics follow the topic’s search intent and funnel stage from the Planner. If you set a value by hand, the brief uses it. Otherwise the Planner value is the starting point, and the brief changes it only when the search results clearly show a different intent.

Paid generation checks the available balance before starting. The assistant should confirm the displayed cost with you first. A pending brief can be cancelled through MCP and its reserved credits refunded; draft cancellation is not currently exposed.

Running the Full Pipeline

An assistant can take a brand from zero to Topical Authority — creating the brand, generating personas, building the site architecture, running topical research, clustering keywords, and building the map:

1. "Create a brand for acme.com — analyze the site"        (brand foundation)
2. "Generate 3 buyer personas"                             (audience insights)
3. "Set the site type to SaaS. Build a SaaS Site + Resources, then generate the architecture"
4. "Set the core topic and run topical research"           (4 generation steps)
5. "Find duplicate topics in the research tree and merge them"
6. Optional: "Run AI Search Gaps — what do the AI engines cover that my tree doesn't?"
   (persona-grounded, cost confirmed first; review the gaps, add the keepers)
7. "Cluster the keywords"                                  (confirms cost first)
8. "Review the clusters — merge anything that overlaps"
9. "Generate the topical map"
10. Decide whether the optional content info snapshots (planning metadata) are useful, then generate them if wanted; confirm the resource URL prefix and generate URL slugs
11. "Advance to Topical Authority"

Things the assistant knows (and will tell you):

• Costs are surfaced before spending. Pipeline clustering enforces a confirmation flag; research, AI Search Gaps, content info, briefs, and drafts expose their cost or estimate so the assistant can get your approval before starting.
• Some steps are one-way. Building the map locks clustering — the assistant surfaces irreversible steps before taking them.
• Research topic steps are free within your plan’s allocation; keyword generation is the stage’s main credit spend.
• Site architecture has a scope choice. A site can continue as “[Site] + Resources”, “Resources Only”, or “[Site] Only” — the labels match your site type (e.g. “SaaS Site + Resources”). The site-only route goes directly to Topical Authority and skips topical research.
• Content info is optional planning metadata. It is useful for prioritization and stakeholder handoffs, but briefs and drafts do not depend on it. Make the choice before Topical Authority, where content-info generation becomes locked.

Managing the Map

“Restructure my topical map.”

These commands drive the Authority Organizer, so they apply once the brand reaches Topical Authority. Before that, map-stage editing is limited to moving, renaming, and deleting clusters.

Ask	What happens
“Move ‘link building strategies’ under the ‘off-page SEO’ pillar”	Re-parents the topic
“Move ‘Topic B’ under the ‘Topic A’ pillar in the Authority Planner”	Same move, phrased the way the app labels it
“Combine ‘SEO audit’ and ‘site audit’ into ‘SEO Site Audit’”	Merges duplicates, keeping both as anchor keywords
“Rename ‘SEO tips’ to ‘Enterprise SEO Best Practices’”	Renames the topic
“Show me all my hierarchy overrides”	Lists the active overrides layered on the base map — each revertible
“Clear all hierarchy overrides”	Undo
“Research and add a silo for ‘programmatic SEO’”	Researches the new cluster; preview the clustering in the app, then the assistant approves the integration
“Add ‘spf record, dkim setup’ to the [topic] node”	Keyword management per node
“Set the slug for that node to ‘email-deliverability-guide’”	Slug update (keep slugs evergreen — no years)
“Fetch search volume for the topics in [cluster]”	Volume, CPC, and competition fetched onto the nodes — estimate shown first

Monitoring Authority & Competitors

“How strong is my topical authority, and who’s beating me?”

Ask	What happens
“Refresh SERP data and recompute authority for [brand]”	Fresh SERPs, updated scores
“Show me TAS scores for each pillar”	Pillar-level breakdown — find the weak areas
“How do I compare against my competitors?”	Competitor metrics side by side
“Which topics cite my brand in AI Overviews?”	AI search citations by topic
“Which topics are we cited or mentioned in AI Overviews?”	Both lists: cited (linked) and mentioned-only, the citability gap between them
“Which topics cite competitor.com in AI Overviews?”	The same view for any domain
“Which pages do AI engines cite for [topic]?”	Every cited source per engine, with whether your brand is mentioned or cited
“Show the top 10 search results for these topics”	Stored results for up to 25 topics at once, with each topic’s fetch date and SERP features
“Show internal linking opportunities for [topic]”	Parent, sibling, and child link targets with relevance and reasoning
“Classify search intents for all topics”	Search intent and funnel stage for every unclassified topic; values you set by hand stay as they are

Loading Client Context

“Load the client’s style guide into Floyi.”

Paste a client’s style guide document into the conversation and have the assistant extract it into Floyi’s Content Guide in one session:

Ask	What happens
“Flag ‘cheap’ as forbidden, prefer ‘affordable’”	Terminology rule
“Add a compliance rule: never promise specific rankings”	Compliance rule
“Never mention [competitor] in content”	Competitor policy
“No exclamation marks in body copy”	Messaging rule
“Add our standard CTA snippet”	Boilerplate

Guide entries feed every subsequent brief and draft for that brand.

“Add these documents to the knowledge base.”

The Content Guide holds rules. The Knowledge Base holds source material: product docs, case studies, research, pricing sheets, anything you want briefs and drafts to write from instead of guessing. Paste the text into the conversation or hand the assistant a URL:

Ask	What happens
“Add this document to the knowledge base for [brand]” (pasted text)	Stored, chunked, and embedded, same as uploading in the app
“Import https://example.com/case-study into the knowledge base”	Fetches the page and stores it
“Import these three pages into the knowledge base” (list of URLs)	One document per URL
“Analyze these three pages to create a detailed doc of data and upload it into the knowledge base”	The assistant reads the pages, writes one consolidated document, and stores that instead of three raw imports
“Create a ‘Case Studies’ category and file those under it”	Category created, documents categorized
“What’s in the knowledge base for [brand]?”	Lists categories and documents with status
“Read the [title] document back to me”	Full text and metadata
“Delete the outdated pricing sheet”	Document removed

Knowledge base tools are free. Once documents are in, “Use persona [name] and pull in the knowledge base” during briefing scopes the brief to that material, and drafts generated from it cite your own research and terminology. File uploads (PDF, DOCX) stay in the app’s Knowledge Base tab; see Brand Foundation.

Publishing

“Publish this finished draft.”

Ask	What happens
“Which WordPress sites can I publish to?”	Connected sites for the workspace
“Publish draft [title] to [site] as a WordPress draft”	Publishes — defaults to WordPress-side draft status, so nothing goes live without review
“Which GitHub repos can I publish to?”	Connected repositories with their branch, content path, and file-format defaults
“Publish draft [title] to my blog repo”	Commits the article as Markdown/MDX straight to the configured branch — the assistant confirms the publish and branch first, since most repos auto-deploy
“Did the publish finish?”	Task status for either channel

Standalone Toolbox

Ask	What happens
“Run an AIRS analysis for ‘best crm for agencies’”	Queries AI search engines, then synthesizes per-engine analysis and strategic recommendations
“Give me the strategic recommendations from that analysis”	Stage-3 output — feed it straight into a brief
“Cluster these 40 keywords for the US market”	Standalone keyword clustering, cost confirmed first
“Which SERP features dominate this keyword set?”	Feature report on a clustering run: top domains and SERP feature counts, with AI Overview presence per keyword

---

Workflow Recipes

Recipe 1: Content Gap to Published Draft

1. "Find content gaps for [brand]"
2. "Generate a brief for the top gap topic. Edit it after it's done"
3. "Check the brief status" (assistant polls until complete)
4. "Generate a draft from the completed brief. Edit the completed draft"
5. "Show me the full draft"
6. "Publish it to my WordPress site as a draft"

With a WordPress connection in place, the whole loop stays in the chat. The edit steps are targeted plain-text curation: the assistant tightens weak sections in the brief before drafting and fixes the draft before publishing, so what lands in WordPress has already been through one review.

An Organic Audit variant starts from what is already working:

1. "What silos are we growing fastest in according to the Organic Audit?"
2. "Which topics should we brief and draft next to complete topical coverage?"
3. Brief, draft, and publish those topics one at a time as above

Recipe 2: Weekly Content Review

1. "Run a weekly report for [brand]"
2. "Show the pipeline overview with credits"
3. "Find the top 5 content gaps"
4. For the top 3, one at a time: generate the brief, review it, then continue to the next

Recipe 3: Content Refresh Triage

Refreshing a page ranking #15 usually beats a net-new article.

1. "Find gaps for [brand], but only weak coverage and low rankings"
2. "For each, confirm the ranking URL and current position"
3. "Show internal linking opportunities for the top 3"
4. After updating: "Refresh authority and check for movement"

Recipe 4: Cannibalization Check

Before writing something new, check whether the map already targets it.

1. "Search my map for topics about '[keyword]'"
2. "Compare the search results for those topics" -> topics that share several ranking pages target the same search
3. If a published topic already targets it -> refresh that page instead (Recipe 3)
4. If two unpublished topics overlap -> "Combine them into one topic"

Recipe 5: Competitor & AI Citation Gap

1. "Who leads on authority — me or my competitors?"
2. "Find contested gaps: topics with high competitor presence where I'm missing"
3. "Which topics cite my domain in AI Overviews? Now the same for competitor.com"
4. "Diff the two lists — where are they cited and I'm not?"
5. Brief the highest-priority topic, review it, then continue through the remaining topics one at a time

Recipe 6: AI Search (GEO) Monitoring

1. "Where am I cited in AI Overviews? Where am I only mentioned?"
2. "Repeat for AI Mode, Gemini, and ChatGPT"
3. Mentioned-but-not-cited topics = citability gap — add stats, definitions,
   and quotable passages to those pages
4. Weekly: "Refresh authority and re-pull the citation counts"

Recipe 7: Production Sprint

Floyi generates deliberately one piece at a time — every brief and draft gets its own cost confirmation and a review before the next starts, so a sprint is a loop, not a batch:

1. "Find all missing topics in the '[cluster]' cluster"
2. "Check my credit balance and estimate the briefs for this list"
3. For each topic: "Generate the brief" -> review it -> curate weak sections
4. "Generate the draft from that brief" -> check its quality scorecard
5. "Stage it in WordPress as a draft" (or commit it to the blog repo)
6. Next topic

Recipe 8: Agency Monday-Morning Digest

Agencies are natural MCP power users when their client brands live in the same Floyi workspace — one conversation can cover every brand visible to that connection.

1. "List all brands with their authority scores"
2. Per brand: "Run the weekly report"
3. "Show competitor movement for each"
4. "Pull AI citation wins to showcase"
5. "Assemble a client-facing summary email for each brand"

This can also become a scheduled digest when the MCP client supplies the scheduler and an email or Slack delivery integration. Floyi MCP provides the brand data and analysis tools; it does not send email or Slack messages by itself.

Recipe 9: Pre-Publish Internal Linking Pass

1. "Show me draft [title]"
2. "Get internal link suggestions for its topic"
3. Add the links in the editor (or verify the draft already includes them)
4. "Publish it as a WordPress draft"

Recipe 10: Load the Knowledge Base, Then Brief

New client, new brand, or a brand whose drafts keep sounding generic. Load the source material first so every brief and draft after it writes from what the brand actually knows.

1. "Add these documents to the knowledge base for [brand]" (paste product docs,
   case studies, or the client's style guide)
2. "Import these three pages into the knowledge base" (URLs)
3. "Create a 'Case Studies' category and file them there"
4. "What's in the knowledge base for [brand]?" (confirm status is Ready)
5. "Find the biggest content gaps for [brand]"
6. "Brief the top gap. Use persona [name] and pull in the knowledge base"
7. "Generate a draft from the completed brief"

Steps 1 through 4 cost nothing. Only the brief and draft in steps 6 and 7 spend credits.

Recipe 11: AI Citation Outreach

Get your brand onto the pages AI engines already cite for the topics that drive revenue.

1. "List the commercial-intent topics in [brand]'s map"
2. "For those topics, collect every page AI Overviews, AI Mode, Gemini, and
   ChatGPT cite, grouped by site"
3. "Drop topics where we're already cited, and rank the sites by how many
   target topics cite them"
4. "For the top sites, draft an outreach email asking them to add [brand]
   to the cited page"

Every step reads stored data and costs nothing. Responses come from your last authority refresh, so refresh first if the data is old. The assistant drafts the outreach; sending it stays with you.

---

What Still Needs the Web App

The MCP server is built for strategy, production, and monitoring. A few things stay in the app on purpose:

Operation	Why
Full rich-text editing, editor-only readback, and visual polish	Assistants can read MCP-readable draft text, curate briefs, and make targeted plain-text edits to sections, intros, and key takeaways. A draft whose body exists only in the rich-text editor is flagged and pointed back to the app. Document structure, rich formatting, links, embeds, visual review, and complete version restore remain in the editor.
Importing a full existing draft	Bring Your Own Draft paste/import remains in the app until Floyi has a safe server-side conversion path into the canonical editor document.
Article images and standalone schema editing	Image generation, placement, cropping, alt-text review, and the complete schema editor remain visual app workflows.
Silo and map visual preview	Assistants can inspect and edit cluster membership and run the coarse silo workflow, while judgment-heavy visual preview steps keep their purpose-built UIs.
Final editorial review	Assistants can set the editorial state, but final visual review and polish still happen in the editor. MCP publishing defaults to a WordPress-side draft.
Knowledge base file uploads (PDF, DOCX)	MCP adds documents from pasted text or a URL. Binary file uploads stay in the Brand Foundation Knowledge Base tab.
Team management, billing, API keys	Account administration stays in Settings.
Creating publishing connections (WordPress, GitHub)	Connections and their credentials are created in the app’s Settings; MCP lists and publishes to them.
Connecting Google Search Console	MCP can read imported GSC insights. OAuth connection, uploads, and reanalysis stay in the Organic Audit app flow.
Historical authority trends and several standalone toolbox screens	MCP exposes current authority data and the AIRS and keyword-clustering toolboxes. Historical TA trends, SERP Insights, Analyze URL, PAA Explorer, and Topical Audit are not currently exposed.

For supported capabilities, connect and ask. The assistant should point you back to the app when a workflow requires visual review, account administration, credentials, or an unexposed import or analytics surface.