The MCP server

Connect a client

Codex

codex mcp add axrush --url https://axrush.com/mcp

Claude Code

claude mcp add --transport http axrush https://axrush.com/mcp

Cursor, and any client that reads an mcp.json

{
  "mcpServers": {
    "axrush": { "url": "https://axrush.com/mcp" }
  }
}

In Claude Desktop, add it as a custom connector with the same URL, under Settings and Connectors.

Anonymous tools

Available to every connection, no key and no account, rate limited like the public API because a scan sends real traffic:

• list_integrations with {}: lists the integration catalogue and each provider’s current availability. Planned providers cannot be connected. No account or repository metadata is returned.
• scan_site with { "domain": "example.com" }: measures a domain and returns text and structured findings, with measurement date, engine version and applicability
• get_report with { "host": "example.com" }: reads the stored public report without sending the site any traffic
• get_agent_tasks with { "host": "example.com" }: reads the task replays a site's owner published
• read_channel with { "handle": "@midudev" }: reads a YouTube channel by handle and returns 8 verdicts rather than a score: identity, about, contact, hub, keywords, captions, chapters, naming; nothing is stored

Your sites, authenticated

Authenticated endpoints cover websites, social identities, exact channels, context and Answers. Each operation checks its own permissions, role, plan and revisions. Reading saved results never starts a paid execution.

An anonymous connection never sees these tools, so an agent is never taught about a door it cannot open. Sign in, then create keys on your account page

• list_my_site_ai_executions with {"site_id":"...","limit":20}: Read saved AI execution metadata: context policy and revision, model usage and outcome. No prompts or context values are returned. Requires the subject’s explicit context-read permission.
• list_my_social_ai_executions with {"identity_id":"...","limit":20}: Read saved AI execution metadata: context policy and revision, model usage and outcome. No prompts or context values are returned. Requires the subject’s explicit context-read permission.
• list_my_social_identities with {}: Manage social identities and channels
• get_my_social_identity with {"identity_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• get_my_social_channel with {"channel_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• get_my_social_channel_connection with {"channel_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• list_my_social_connection_options with {"channel_id":"00000000-0000-4000-8000-000000000001","session_id":"00000000-0000-4000-8000-000000000002"}: Manage social identities and channels
• select_my_social_connection_option with {"channel_id":"00000000-0000-4000-8000-000000000001","session_id":"00000000-0000-4000-8000-000000000002","option_id":"123456789","expectedIdentityRevision":1,"expectedChannelRevision":1}: Manage social identities and channels
• cancel_my_social_connection with {"channel_id":"00000000-0000-4000-8000-000000000001","session_id":"00000000-0000-4000-8000-000000000002"}: Manage social identities and channels
• create_my_social_identity with {"requestId":"00000000-0000-4000-8000-000000000002","identityKind":"brand","name":"Example Brand","channel":{"platform":"youtube","handle":"example"},"siteId":null}: Manage social identities and channels
• set_my_social_identity_kind with {"identity_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"identityKind":"brand"}: Manage social identities and channels
• set_my_social_identity_site with {"identity_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"siteId":null}: Manage social identities and channels
• delete_my_social_identity with {"identity_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1}: Manage social identities and channels
• add_my_social_channel with {"identity_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1,"platform":"youtube","handle":"example"}: Manage social identities and channels
• update_my_social_channel with {"channel_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"expectedChannelRevision":1,"handle":"example"}: Manage social identities and channels
• remove_my_social_channel with {"channel_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1,"expectedChannelRevision":1}: Manage social identities and channels
• set_my_social_channel_watching with {"channel_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"expectedChannelRevision":1,"watched":true}: Manage social identities and channels
• read_my_channel with {"channel_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1,"expectedChannelRevision":1}: Manage social identities and channels
• get_my_reading with {"reading_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• list_my_channel_readings with {"channel_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• get_my_channel_documents with {"channel_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• verify_my_channel_document with {"channel_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1,"expectedChannelRevision":1,"document":"description"}: Manage social identities and channels
• list_my_channel_verifications with {"channel_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• add_my_social_rival with {"identity_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1,"rivalId":"00000000-0000-4000-8000-000000000002"}: Manage social identities and channels
• remove_my_social_rival with {"identity_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"rivalId":"00000000-0000-4000-8000-000000000002"}: Manage social identities and channels
• list_my_social_rivals with {"identity_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• disconnect_my_social_channel with {"channel_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1,"expectedChannelRevision":1}: Manage social identities and channels
• get_my_social_removal with {"operation_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• list_my_social_alert_rules with {"identity_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• save_my_social_alert_rule with {"identity_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"ruleId":"00000000-0000-4000-8000-000000000002","type":"mention_drop","threshold":10,"checkId":null,"enabled":true,"notifyEmail":true,"webhookUrl":null}: Manage social identities and channels
• delete_my_social_alert_rule with {"identity_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"ruleId":"00000000-0000-4000-8000-000000000002"}: Manage social identities and channels
• get_my_social_alert_secret with {"identity_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"ruleId":"00000000-0000-4000-8000-000000000002"}: Manage social identities and channels
• get_my_social_answer_questions with {"identity_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• save_my_social_answer_questions with {"identity_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"expectedRevision":0,"questions":[{"text":"What does Example Brand offer?","kind":"accuracy","active":true}]}: Manage social identities and channels
• get_my_social_answer_settings with {"identity_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• set_my_social_answer_settings with {"identity_id":"00000000-0000-4000-8000-000000000001","expectedIdentityRevision":1,"expectedRevision":0,"cadence":"off","engines":["openai"]}: Manage social identities and channels
• get_my_social_answer_options with {"identity_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• run_my_social_answers with {"identity_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1,"engines":["openai"]}: Manage social identities and channels
• run_my_social_answer_gift with {"identity_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1}: Manage social identities and channels
• suggest_my_social_answer_questions with {"identity_id":"00000000-0000-4000-8000-000000000001","requestId":"00000000-0000-4000-8000-000000000002","expectedIdentityRevision":1}: Manage social identities and channels
• get_my_social_answer_suggestion with {"identity_id":"00000000-0000-4000-8000-000000000001","suggestion_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• get_my_social_answers with {"identity_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• get_my_social_answer_pass with {"identity_id":"00000000-0000-4000-8000-000000000001","pass_id":"00000000-0000-4000-8000-000000000001"}: Manage social identities and channels
• get_my_site_artifact_options with {"site_id":"..."}: Inspect generation options, then explicitly confirm scope, AI use and replacement to reserve a durable operation. Follow its status and paginated history. Saved-file reads withhold stale or unknown bodies. Requires artifact read/write consent for OAuth; generation never publishes a site.
• generate_my_site_artifacts with {"site_id":"...","idempotencyKey":"...","expectedFingerprint":"...","scope":"llms-only","allowAi":false,"replaceExisting":false}: Inspect generation options, then explicitly confirm scope, AI use and replacement to reserve a durable operation. Follow its status and paginated history. Saved-file reads withhold stale or unknown bodies. Requires artifact read/write consent for OAuth; generation never publishes a site.
• get_my_site_artifact_generation with {"site_id":"...","operation_id":"..."}: Inspect generation options, then explicitly confirm scope, AI use and replacement to reserve a durable operation. Follow its status and paginated history. Saved-file reads withhold stale or unknown bodies. Requires artifact read/write consent for OAuth; generation never publishes a site.
• list_my_site_artifact_generations with {"site_id":"...","page":1}: Inspect generation options, then explicitly confirm scope, AI use and replacement to reserve a durable operation. Follow its status and paginated history. Saved-file reads withhold stale or unknown bodies. Requires artifact read/write consent for OAuth; generation never publishes a site.
• list_my_site_artifacts with {"site_id":"..."}: Inspect generation options, then explicitly confirm scope, AI use and replacement to reserve a durable operation. Follow its status and paginated history. Saved-file reads withhold stale or unknown bodies. Requires artifact read/write consent for OAuth; generation never publishes a site.
• get_my_artifact with {"site_id":"...","kind":"llms_txt"}: Inspect generation options, then explicitly confirm scope, AI use and replacement to reserve a durable operation. Follow its status and paginated history. Saved-file reads withhold stale or unknown bodies. Requires artifact read/write consent for OAuth; generation never publishes a site.
• generate_my_site_markdown_draft with {"site_id":"...","contextRevision":1,"bindingRevision":1,"idempotencyKey":"...","allowAi":true}: Generate a paid homepage Markdown draft from public context and verified source evidence, or read its saved result. Review and confirm public content before preparing a PR.
• get_my_site_markdown_draft with {"site_id":"...","draft_id":"..."}: Generate a paid homepage Markdown draft from public context and verified source evidence, or read its saved result. Review and confirm public content before preparing a PR.
• verify_my_site_remediation with {"site_id":"...","operation_id":"...","expectedRevision":1,"idempotencyKey":"..."}: Read private corrections and exact diffs. Write access prepares and approves supported recipes; security.txt needs security consent and Content Negotiation needs source consent and confirmed public Markdown. A draft PR requires exact-manifest approval, owner/admin role, paid website coverage and repository access. Separate verify consent enables bounded post-merge public-content checks and a fresh indicator review, without changing original/global scores or proving deployment or CI. Approve verifyAfterMerge is optional and false by default. No AI, merge or deployment is included.
• list_my_site_remediations with {"site_id":"...","page":1}: Read private corrections and exact diffs. Write access prepares and approves supported recipes; security.txt needs security consent and Content Negotiation needs source consent and confirmed public Markdown. A draft PR requires exact-manifest approval, owner/admin role, paid website coverage and repository access. Separate verify consent enables bounded post-merge public-content checks and a fresh indicator review, without changing original/global scores or proving deployment or CI. Approve verifyAfterMerge is optional and false by default. No AI, merge or deployment is included.
• get_my_site_remediation with {"site_id":"...","operation_id":"..."}: Read private corrections and exact diffs. Write access prepares and approves supported recipes; security.txt needs security consent and Content Negotiation needs source consent and confirmed public Markdown. A draft PR requires exact-manifest approval, owner/admin role, paid website coverage and repository access. Separate verify consent enables bounded post-merge public-content checks and a fresh indicator review, without changing original/global scores or proving deployment or CI. Approve verifyAfterMerge is optional and false by default. No AI, merge or deployment is included.
• save_my_site_remediation_inputs with {"site_id":"...","kind":"security_txt","expectedRevision":0,"contact":"mailto:security@example.com","expires":"2027-01-01T00:00:00Z"}: Read private corrections and exact diffs. Write access prepares and approves supported recipes; security.txt needs security consent and Content Negotiation needs source consent and confirmed public Markdown. A draft PR requires exact-manifest approval, owner/admin role, paid website coverage and repository access. Separate verify consent enables bounded post-merge public-content checks and a fresh indicator review, without changing original/global scores or proving deployment or CI. Approve verifyAfterMerge is optional and false by default. No AI, merge or deployment is included.
• prepare_my_site_remediation with {"site_id":"...","scanId":"...","artifactId":"...","bindingRevision":1,"idempotencyKey":"..."}: Read private corrections and exact diffs. Write access prepares and approves supported recipes; security.txt needs security consent and Content Negotiation needs source consent and confirmed public Markdown. A draft PR requires exact-manifest approval, owner/admin role, paid website coverage and repository access. Separate verify consent enables bounded post-merge public-content checks and a fresh indicator review, without changing original/global scores or proving deployment or CI. Approve verifyAfterMerge is optional and false by default. No AI, merge or deployment is included.
• approve_my_site_remediation with {"site_id":"...","operation_id":"...","expectedRevision":1,"patchHash":"...","verifyAfterMerge":false}: Read private corrections and exact diffs. Write access prepares and approves supported recipes; security.txt needs security consent and Content Negotiation needs source consent and confirmed public Markdown. A draft PR requires exact-manifest approval, owner/admin role, paid website coverage and repository access. Separate verify consent enables bounded post-merge public-content checks and a fresh indicator review, without changing original/global scores or proving deployment or CI. Approve verifyAfterMerge is optional and false by default. No AI, merge or deployment is included.
• cancel_my_site_remediation with {"site_id":"...","operation_id":"...","expectedRevision":1}: Read private corrections and exact diffs. Write access prepares and approves supported recipes; security.txt needs security consent and Content Negotiation needs source consent and confirmed public Markdown. A draft PR requires exact-manifest approval, owner/admin role, paid website coverage and repository access. Separate verify consent enables bounded post-merge public-content checks and a fresh indicator review, without changing original/global scores or proving deployment or CI. Approve verifyAfterMerge is optional and false by default. No AI, merge or deployment is included.
• retry_my_site_remediation with {"site_id":"...","operation_id":"...","expectedRevision":1}: Read private corrections and exact diffs. Write access prepares and approves supported recipes; security.txt needs security consent and Content Negotiation needs source consent and confirmed public Markdown. A draft PR requires exact-manifest approval, owner/admin role, paid website coverage and repository access. Separate verify consent enables bounded post-merge public-content checks and a fresh indicator review, without changing original/global scores or proving deployment or CI. Approve verifyAfterMerge is optional and false by default. No AI, merge or deployment is included.
• list_my_integrations with {}: read authorized accounts and paginated repositories, or read, save and remove versioned site repository connections. Requires owner/admin authorization and explicit integration scopes for OAuth. These tools do not edit files, open pull requests, merge or deploy.
• list_my_repositories with {"connection_id":"...","page":1}: read authorized accounts and paginated repositories, or read, save and remove versioned site repository connections. Requires owner/admin authorization and explicit integration scopes for OAuth. These tools do not edit files, open pull requests, merge or deploy.
• get_my_site_repository with {"site_id":"..."}: read authorized accounts and paginated repositories, or read, save and remove versioned site repository connections. Requires owner/admin authorization and explicit integration scopes for OAuth. These tools do not edit files, open pull requests, merge or deploy.
• set_my_site_repository with {"site_id":"...","connectionId":"...","repositoryId":123,"branch":"main","rootDirectory":"","productionUrl":"https://example.com","expectedRevision":0}: read authorized accounts and paginated repositories, or read, save and remove versioned site repository connections. Requires owner/admin authorization and explicit integration scopes for OAuth. These tools do not edit files, open pull requests, merge or deploy.
• disconnect_my_site_repository with {"site_id":"...","expectedRevision":1}: read authorized accounts and paginated repositories, or read, save and remove versioned site repository connections. Requires owner/admin authorization and explicit integration scopes for OAuth. These tools do not edit files, open pull requests, merge or deploy.
• get_my_context with {"site_id":"..."}: Read private context, provenance, revisions, usage and automation, even before the first scan.
• get_my_context_history with {"site_id":"..."}: Read research activity in pages of five. Pass the returned older or newer cursor with its direction.
• get_my_context_job with {"site_id":"...","jobId":"..."}: Read a real context job and its proposal or source comparison. Poll no more than once every five seconds.
• save_my_context with {"site_id":"...","expectedRevision":0,"document":{"name":"Example","description":"","audience":"","languages":"","offerings":"","goals":"","facts":"","constraints":""}}: Save the complete context document at its current revision. Preserve unchanged fields.
• run_my_context with {"site_id":"...","kind":"research","requestId":"...","locale":"en"}: Start paid AI research or a source comparison. Reuse requestId only to retry the same request. Plan limits apply.
• apply_my_context_proposal with {"site_id":"...","jobId":"...","expectedRevision":0,"fields":["description"]}: Accept selected proposal fields at the expected revision. This does not edit the website.
• set_my_context_preferences with {"site_id":"...","expectedRevision":1,"field":"description","protected":true,"visibility":"private"}: Change field protection or visibility at the current revision. Publishing a field requires explicit user intent.
• set_my_context_policy with {"site_id":"...","expectedRevision":0,"policy":{"cadence":"off","autoApply":"off","monthlyLimit":12,"assessAnswers":false}}: Configure cadence, auto-acceptance and budget. Owner/admin only; enabled automation requires paid coverage.
• get_my_social_context with {"identity_id":"..."}: Read private brand or creator identity, topics, audience, business facts, field provenance, privacy, revision, automation and usage. Works before a first channel reading. Requires the separate social-context read grant.
• get_my_social_context_history with {"identity_id":"..."}: Read five social identity research or comparison jobs with stable pagination. Returns evidence excerpts and source metadata, never raw model output or source bodies.
• get_my_social_context_job with {"jobId":"...","identity_id":"..."}: Read the real status, proposal, evidence or findings of one social identity context job. Poll no faster than every five seconds and stop when ready, failed or cancelled.
• save_my_social_context with {"expectedRevision":0,"document":{"name":"Example","description":"","audience":"","languages":"","offerings":"","goals":"","facts":"","constraints":"","aliases":"","topics":"","affiliations":"","businessContact":"","sponsorshipPolicy":""},"identity_id":"...","expectedIdentityRevision":1}: Replace the social identity context at expectedRevision. Preserve unrequested fields. Corrections become protected. Legacy social declarations are projections of this document; historical channel checks and answers remain unchanged.
• run_my_social_context with {"kind":"research","requestId":"...","locale":"en","identity_id":"...","expectedIdentityRevision":1}: Start paid research from current supported channel readings and an optional linked public hub, or compare that evidence and independent agent answers with context. Requires active paid channel coverage. Use a unique requestId, reused only for retries. Budgets, cooldown and a single active job apply. Returns a jobId, not a finished result.
• apply_my_social_context_proposal with {"jobId":"...","expectedRevision":0,"fields":["description"],"identity_id":"...","expectedIdentityRevision":1}: Apply explicitly selected fields from a ready social identity research proposal at expectedRevision after reviewing evidence and conflicts. Requires active paid channel coverage and current sources. Does not publish to a channel or change measured answers.
• set_my_social_context_preferences with {"expectedRevision":1,"field":"description","protected":true,"visibility":"private","identity_id":"...","expectedIdentityRevision":1}: Change protection and public/private visibility of a social identity context field at expectedRevision. Private is the default. Make public only when the user explicitly requests it.
• set_my_social_context_policy with {"expectedRevision":0,"policy":{"cadence":"off","autoApply":"off","monthlyLimit":12,"assessAnswers":false},"identity_id":"...","expectedIdentityRevision":1}: Configure social identity research cadence, budget, automatic acceptance and answer comparisons at the policy expectedRevision. Owner/admin only. Enabling requires active paid channel coverage and social-context run scope. Obtain the intended schedule and budget before enabling.
• list_my_sites with {}: lists your sites with their ids and latest scores
• get_my_report with { "site_id": "..." }: the latest full report for one of your sites, pages included
• get_my_history with { "site_id": "..." }: the score history with the engine version on every row
• scan_my_site with { "site_id": "..." }: queues a scan of your own site and returns its id at once
• get_my_scan with { "scan_id": "..." }: polls one scan until it settles; succeeded carries the full report
• get_my_fixes with { "site_id": "..." }: the open work on one site, ordered by the points each fix returns
• get_my_fix with { "site_id": "...", "check_id": "llms-txt" }: every finding behind one check, its guide, and the whole fix as one prose block
• compare_my_scans with { "site_id": "..." }: compares the latest two finished scans; optionally supply both before_scan_id and after_scan_id. Reports resolved origin checks, regressions, and warnings when the engine or coverage changed
• get_my_verifications with { "site_id": "..." }: reads existing fix verification records without scheduling work
• get_my_answers with { "site_id": "..." }: lists stored Answers passes and reads the latest finished one; pass_id selects another pass, including one still running
• get_my_agent_runs with { "site_id": "..." }: reads stored agent runs, including unpublished ones, with verdicts, answers and evidence; run_id selects one run

Connect with your key

Codex

codex mcp add axrush --url https://axrush.com/mcp --bearer-token-env-var AXRUSH_API_KEY

Set AXRUSH_API_KEY to your organization API key in the environment that launches Codex, then restart the client. Codex sends it as a bearer token.

Claude Code

claude mcp add --transport http axrush https://axrush.com/mcp \
  --header "Authorization: Bearer axr_..."

Cursor, and any client that reads an mcp.json

{
  "mcpServers": {
    "axrush": {
      "url": "https://axrush.com/mcp",
      "headers": { "authorization": "Bearer axr_..." }
    }
  }
}

Read, fix, verify

Start with list_my_sites and get_my_report. Read get_my_fixes, then get_my_fix for the selected check. After publishing your changes, call scan_my_site and poll get_my_scan after pollAfterSeconds. Use the baseline and completed scan ids with compare_my_scans. Comparisons cover origin findings; a changed engine or page coverage prevents declaring fixes or regressions confirmed.

Every tool returns readable text and structuredContent matching its outputSchema, with a nextStep. Check isError first: errors contain an error code and message. N/A checks have applicable=false and score=null, and do not count as failures.

list_my_site_ai_executions, list_my_social_ai_executions, list_my_social_identities, list_my_channel_readings, list_my_channel_verifications, list_my_social_rivals, get_my_social_answers, list_my_sites, get_my_history, get_my_verifications, get_my_answers, and get_my_agent_runs accept limit (1–50, default 20) and offset (default 0). Repeat with nextOffset as offset and the same limit until nextOffset is null. In Answers, pagination applies to the pass list; selectedPass identifies the pass whose results are returned.

Native clients need no Origin header. Browser clients must use the site origin or an origin explicitly allowed by the deployment. Supported MCP protocol versions: 2025-06-18 and 2025-03-26. The endpoint is stateless and accepts JSON requests up to 64 KiB.