Feature · SEO MCP

SEO MCP Tools for Teams

The AmICited MCP server exposes live workspace tools — so Claude Code, Cursor, Codex and ChatGPT can read AI visibility, search, traffic, and reporting data, then take permitted actions where you work. It uses a workspace URL and OAuth connection; the catalog is read from the running server rather than copied from an internal REST API.

amicited.com/mcp
AmICited MCP connection panel with server URL and the live 48-tool catalogue
Live MCP surface
Dashboard catalogue Full registered server surface
MCP client default Core plus five discovery tools
Discover Toolsets, search, schema
Invoke Read tool or scoped action
The dashboard shows the whole catalogue; clients receive a compact starting surface so the definitions do not crowd out the work.
Model Context Protocol

SEO MCP Tools

AmICited exposes articles, annotations, prompts, citations, sources, competitors, analytics, fan-outs, ranked keywords, freshness, Web Vitals, accessibility, performance impact, and connected reporting as live MCP tools. They have their own schemas, validation, permissions, and scopes, not a general public REST interface.

  • Dashboard versus client — the dashboard derives a full live catalogue; default tools/list gives clients only the core and five discovery tools.
  • Discover progressively — use list_toolsets, search_tools, and describe_tool, then read_tool or run_tool; pin areas with ?toolsets= or use ?toolsets=all.
  • Read is the default — read-only OAuth can discover and invoke read tools; mutations need the separate write grant.
  • Evidence, not attribution — a tool result informs an investigation. It does not prove one SEO action caused an outcome.
Organic search, content, and indexing

Organic Search Tools

Read Google Search Console and Bing Webmaster reporting, then work through traffic and content evidence before choosing a technical action. The report surface includes Click Waterfall, Unified Pages and Keywords, directories, movers, Decay & Growth, Query Coverage, Index Bloat, Content Changes, N-Grams, Cannibalization, CTR and citation gaps, paid gaps, and share of search.

  • Inspect before submitting — crawl and URL-inspection evidence are distinct from Google indexing, Bing submission, or IndexNow actions.
  • Keep engines distinct — Google and Bing are not blended into an incompatible single result.
  • Carry the caveats — anonymised queries, incomplete imports, fitted curves, and missing evidence constrain the answer.
  • Confirm the request, not the outcome — a submission does not guarantee crawling, indexing, ranking, traffic, or citation.
Organic investigation surface
Google Search Console Overview, queries, pages, directories, sitemaps and inspection
Bing Webmaster Search reports, crawl data and URL submission
IndexNow Settings, key verification and submission
Traffic reports Waterfall, movers, directories, decay and gaps
Connected-source coverage and report windows still define what each answer can say; a missing connection is not a zero result.
Commercial reporting surface
E-commerce Orders, products, customers, retention, LTV, costs and profitability
Google and Bing Ads Overview, keywords, search terms, campaigns and breakdowns
Meta Ads Attribution, profit, CAC, audience, saturation, dayparting and scaling
ChatGPT Ads Account, campaigns, ad groups, creatives, conversions, insights and bulk jobs
Every commercial answer depends on the connected account, imported coverage, and available cost or order data; MCP does not manufacture a profit basis.
Commerce and paid media, where connected

Bring commercial evidence into the same review: e-commerce covers orders, products, customers, retention, LTV, costs, and profitability; Google and Bing Ads cover their reporting suites; Meta covers attribution, profit, CAC, audiences, saturation, dayparting, and scaling. ChatGPT Ads adds account, campaign, creative, conversion, insight, and bulk-job tools.

  • Profit needs inputs — cost mapping, order data, and attribution coverage qualify every commercial result.
  • Bulk stays observable — submit a job, then read its operations and status instead of assuming every change landed.
  • Compare without claiming cause — matching paid and organic movement forms a hypothesis, not attribution.
  • Providers remain in control — their rules, quotas, credits, and delivery outcomes still apply.
Workspace operations and availability

Uptime and Workspace Tools

Manage the surrounding operating context: tracked domains, tags, competitors, connections, import options, sync status, previews, inbox state, and prompt suggestions. Availability tools add monitors, checks, incidents, heartbeats, status pages, maintenance windows, subscribers, and SLA reporting.

  • Workspace binding comes first — every request resolves in the connected workspace, not a copied identifier.
  • Plan limits remain active — monitor and status-page creation can still be capped.
  • Maintenance is a declaration — it can suppress planned incident noise, not prove a deployment was harmless.
  • Availability is a lead, not SEO attribution — an incident can focus investigation without proving a traffic cause.
Operations tool families
Workspace and domains Domains, tags, competitors, connections, imports and inbox
Uptime Monitors, checks, incidents, alerts and badge controls
Heartbeats Expected job signals and incidents
Status pages Public status pages, subscribers, maintenance and SLA reports
Operational tools stay scoped to the authenticated workspace or selected domain; a monitor or status-page action is not a substitute for reviewing the affected service.
Built-in playbooks, not a blank tool list

MCP Skills and Workflows

Built-in skill:// resources turn a catalogue into a repeatable review. Start with using-amicited, then choose AI visibility audit, competitor-gap analysis, traffic-drop triage, indexing triage, cannibalization cleanup, paid-waste review, profitability, customer value, SEO-to-revenue, recurring reports, uptime setup, onboarding, prompt-set design, or “did our change work?”.

  • Ask for scope first — skills prompt for date windows, connection state, and caveats before a summary.
  • Keep evidence separate — traffic reviews retain demand, position, CTR, and coverage; content reviews retain observation versus causality.
  • Route, do not bypass — a skill selects tools but cannot evade OAuth, workspace permissions, quotas, or confirmations.
  • Repeat the check — owners get a consistent workflow while experts can inspect the supporting rows.
MCP skill resources
Start with click movement and data coverage
Traffic drop triage
Separate crawl, inspection and submission
Indexing triage
Compare competing URLs before consolidating
Cannibalization cleanup
Use fixed windows and carry caveats forward
Recurring reports
Skills are server-provided `skill://` guidance that tells an MCP client which tools and checks fit a workflow; they do not run changes by themselves.
Requests that map to skills
Why did traffic fall?Read first, then investigate Traffic drop triage
Should we submit this URL?Inspect before a write Indexing triage
Did the rewrite work?Compare evidence, not causality Did our change work
Where is paid spend wasted?Read results before provider changes Paid-waste review
What is profitable?State cost and coverage limits Profitability deep dive / customer value
Create a weekly reportFixed windows and caveats Recurring reports
Skills guide a request to evidence and the right tool family. They do not silently mutate a workspace, submit a URL, or change an ad account.
Ask a practical question, keep control of the action

AI Agent Use Cases

Claude Desktop and ChatGPT connectors are conversational clients; Claude Code is a terminal and coding agent; Cursor and VS Code Copilot Agent are IDE agents; and FlowHunt runs workflow agents. These six guided clients have setup snippets. Codex and other standards-compatible MCP clients can use the same workspace endpoint without a dedicated snippet. Ask for a domain, window, and decision, then let a skill find the relevant evidence.

“Why did clicks fall?” maps to traffic-drop-triage. “Should we submit this URL?” uses indexing-triage to inspect first. “Did the rewrite work?” uses did-our-change-work. Paid-waste-review, profitability-deep-dive, customer-value, uptime-setup, and recurring-reports cover the matching commercial and operational questions.

  • Read before action — reports, inspection, status, and schemas precede a write.
  • Keep writes separate — indexing, submissions, provider changes, and workspace updates need write scope, validation, and may meet provider, plan, quota, or credit limits.
  • Confirm the request, not the result — acceptance does not prove crawling, rankings, profit, recovery, or citation.
  • Hand off the evidence — return the window, coverage, warnings, and relevant rows for review.
Connection safeguards
Read scope Connect and use read tools
Write scope Required in addition for mutations
Workspace binding Token must match the URL workspace
Plan gate AmICited Pro or above
Workspace API keys predate OAuth scopes and carry workspace access; OAuth connections remain scoped and revocable.
Access, scopes, and consequences

MCP Access and Security

OAuth tokens must be live, bound to the workspace URL, and carry the read scope. Writes need the additional write scope; the workspace owner needs AmICited Pro or above. A workspace API key is a fallback with workspace access rather than OAuth’s split grants.

  • Read-only stays read-only — it can explore but cannot create, change, or delete.
  • Tool kinds are visible — read, write, destructive, and external distinguish a report lookup from a deletion, submission, or credit-using call.
  • Revocation ends the token family — remove a grant when a client should no longer connect.
  • Permissions still apply — MCP does not turn a restricted action into an allowed one.
MCP

One server, every AI client

Claude Desktop, Claude Code, ChatGPT connectors, Cursor, VS Code Copilot Agent and FlowHunt each speak MCP with a ready-made setup snippet. Connect AmICited once — via OAuth, or an API key as fallback — and your visibility data is available in all of them.

See the SEO agents

SEO MCP Workflow

Connect the AmICited MCP server to Claude Code, Cursor, Codex or FlowHunt and query your prompts, ranks and citations as live tools — right where you build.

amicited.com/mcp
AmICited MCP connection panel with server URL and the live 48-tool catalogue

Wire AI visibility into your workflow

Free check · 7-day trial · card required