SearchChampSearchChamp
MCP Documentation

MCP tool reference

Parameters, returned data, scopes, costs, and availability for every SearchChamp MCP tool.

SearchChamp publishes 38 tools from one versioned registry. OAuth clients receive the full catalog; each call still checks scope and role. User-generated tokens receive only the tools marked in the Token column, filtered by the organization's current plan and the token's scope.

Input and result rules

  • Inputs are strict: unknown fields, wrong types, out-of-range numbers, and malformed UUIDs return invalid_input before the handler runs.
  • A site accepts a domain or display name. Call list_sites when unsure. A foreign/missing site returns site_not_found; an ambiguous name returns only your own matching candidates.
  • Tool results contain human-readable content and machine-readable structuredContent.
  • A missing product prerequisite is normally a valid { setup_required: true, reason, next_step } result, not an exception.
  • Credits are debited after a handler runs. Denied/invalid calls do not debit a successful tool call.

Core SEO reads

ToolRequired input and optional boundsReturned dataScopeCreditsToken
list_sitesNoneAddressable sites: slug, domain, workspacemcp:read1All paid plans
get_daily_briefsite; date? as YYYY-MM-DDHeadline, findings, open actions, or setup guidancemcp:read1OAuth only
get_site_snapshotsiteRank/AI Visibility/audit/credit rollup plus open actions, goals, and strategy cardsmcp:read1OAuth only
get_rank_moverssite; days? 1–90 (default 7), limit? 1–100 (default 10)Keywords ordered by movement, including baseline/current ranks and deltamcp:read1OAuth only
get_rankingsSame as get_rank_moversSame rank-mover data under the token-catalog namemcp:read1All paid plans
get_ai_visibilitysiteScore, prompt coverage, appearance/share-of-voice summary, or setup guidancemcp:read1All paid plans
get_opportunitiessite; limit? 1–100 (default 10)Top active opportunities with title, lane, and impactmcp:read1OAuth only
get_audit_summarysiteLatest completed audit scores and severity counts, or setup guidancemcp:read1OAuth only
get_audit_issuessite; limit? 1–100 (default 20)Actual severity-ordered findings: title, page URL, description, kind/lens, and fix availabilitymcp:read1Business/Pro+ token
get_backlinks_summarysiteActive total, 30-day gained/lost, spam count, top referring domainsmcp:read1Business/Pro+ token
get_tracked_keywordssite; limit? 1–500 (default 50)Current positions, unranked flags, volumes, and cluster labelsmcp:read1OAuth only
get_bot_access_reportsiteLatest AI Access Score, per-bot verdict/evidence, grouped coverage, recent history; { report: null } if no scanmcp:read1OAuth only
get_volatilitysite; days? 1–90 (default 30)Volatility score and most-volatile keywords, or setup guidancemcp:read1Business/Pro+ token

Content and publishing

ToolRequired input and optional boundsReturned data / effectScopeCreditsToken
get_content_draftssite; limit? 1–100 (default 25)Draft/ready article identifiers, slugs, statuses, and titlesmcp:read1Business/Pro+ token
list_draft_articlessite; limit? 1–100 (default 25)Drafts plus MCP claim state: unclaimed, claimed/lease, or published/verificationmcp:read1OAuth only
get_article_contentarticle_idMarkdown/HTML body, SEO metadata, slug, hero image, and publisher JSON-LD graphmcp:read1OAuth only
get_page_recommendationssite; url?Audit issues and opportunities reshaped as rewrite guidancemcp:read1OAuth only
get_brand_voicesiteComposed tone, do/don't lists, banned phrases, audience, and available named voicesmcp:read1OAuth only
start_publisharticle_idClaims a draft for 30 minutes; returns claimed/reclaimed/already-claimed statemcp:act10OAuth only
report_publisharticle_id, canonical_url on the site's domainRecords the external publish and queues independent verification; idempotent for article+URLmcp:act10OAuth only
publish_articlearticle_id, provider (wordpress or shopify); as_draft? default falseSearchChamp enqueues its standard CMS publisher and returns job_id; feature-enable and CMS gates applymcp:act10OAuth only

start_publish/report_publish are for a coding agent that performs the site write itself. publish_article asks SearchChamp to perform the CMS write. Poll get_job after publish_article.

Custom-site publication artifacts

ToolRequired input and optional boundsReturned dataScopeCreditsToken
list_pending_publication_pagessite; limit? 1–100 (default 25), offset? 0–10,000Exact total and bounded page of Content Writer pages awaiting custom-site publicationmcp:read1Business/Pro+ token
get_pending_publication_pagesite, article_id UUIDSource/proposed versions and a drift-safe ChangeArtifactV1mcp:read1Business/Pro+ token
list_internal_link_editssite; limit? 1–100 (default 25), offset? 0–10,000Exact total and bounded pending edits without full page bodiesmcp:read1Business/Pro+ token
get_internal_link_editsite, suggestion_id UUIDExact-context, drift-safe ChangeArtifactV1mcp:read1Business/Pro+ token

Page Optimizer apply and verification

ToolRequired input and optional boundsReturned data / effectScopeCreditsToken
list_approved_changessite; approved status?; limit? 1–100 (default 25)Approved changes with page/section identity, summary, lifecycle status, and verification timestampsmcp:read1Business/Pro+ token
get_changeidExact approved before/after HTML, page URL, anchor, heading, kind, summary, selector hints, and statusmcp:read1Business/Pro+ token
mark_appliedidReports a live application and triggers an independent re-crawl; settles verified or applied-unverifiedmcp:act10OAuth only

list_approved_changes defaults to approved but not conclusively verified work (accepted, applied, and applied_unverified). mark_applied never accepts HTML from the caller and is rate-bounded/idempotent; the agent's report is not the final verification.

llms.txt

ToolRequired input and optional boundsReturned data / effectScopeCreditsToken
get_llms_txtsiteCurrent configuration/content and latest generation statemcp:read1Business/Pro+ token
generate_llms_txtsite, idempotency_key 1–128 charsCreates or reuses a generation jobmcp:spend20Business/Pro+ Full token
get_llms_txt_jobsite, run_id UUIDOne site-scoped generation jobmcp:read1Business/Pro+ token
list_llms_txt_versionssite; limit? 1–100 (default 25), offset? 0–10,000Exact total and bounded generated-version listmcp:read1Business/Pro+ token
diff_llms_txt_versionssite, from_version_id, to_version_id UUIDsExact unified diff between two versions from the same sitemcp:read1Business/Pro+ token

The caller supplies a stable idempotency_key so reconnects/retries do not enqueue equivalent generation work twice.

Actions, natural-language answers, and jobs

ToolRequired inputReturned data / effectScopeCreditsToken
list_actionssite; status?Site agent actions, optionally filteredmcp:read1OAuth only
approve_actionaction_idAudited, idempotent approval. Eligible CMS meta writes can execute only when mcp:act is also granted and execution is enabled; spending runs otherwise remain proposed for in-app approvalmcp:approve5OAuth only
decline_actionaction_idAudited, idempotent declinemcp:approve5OAuth only
ask_atliosite, messageGrounded answer plus suggested actions (capability, params, billing preview, action class); spending commands are proposed, not silently runmcp:read20OAuth only
get_jobjob_idStatus, stage, percent, partial summary, and poll_after_ms; poll until succeeded/failed/canceledmcp:read1OAuth only

ask_atlio requires editor-or-higher access to the addressed site. Although it requires the read scope, it is LLM-backed and costs 20 credits. The server's published cost is authoritative if this table and a live tools/list ever differ.

Token catalog summary

User-generated tokens intentionally expose a smaller catalog:

  • Every paid plan: list_sites, get_rankings, get_ai_visibility.
  • Business/Pro and higher: also get_audit_issues, get_backlinks_summary, get_content_drafts, get_volatility, the approved-change read tools, custom-publication artifact reads, and llms.txt reads.
  • Business/Pro and higher Full tokens: also generate_llms_txt through mcp:spend.
  • Approval, action-decision, ask_atlio, mark_applied, and publishing tools are OAuth-only.

The organization plan is evaluated at call time. Downgrading can immediately reduce a token's visible catalog; upgrading expands it without reminting the token.

On this page