The MCP tool directory.

Retrieves internal anchor text data for a given website or URL, detailing how anchor texts are used in links between pages on the same site. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves information about external domains that are linked from a specified target domain or URL, allowing for filtering, field selection, and various scopes of analysis. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Provides SEO performance metrics for a specified domain, URL, or site section as of a given date, with options to customize search scope, protocol, country, and search volume mode. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves historical data on key organic and paid search traffic and cost metrics for a specified domain, URL, or path over a selectable date range and grouping interval. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves a list of organic search competitors for a specified website or URL, providing comparative SEO metrics such as common keywords, traffic estimations, and domain strength for a chosen country and date. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves detailed organic keyword data for a given domain, URL, or path, including rankings, search intent, SERP features, traffic and CPC metrics, with the ability to filter, sort, and compare metrics across dates and regions. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves statistical data about the outbound links (outlinks) from a specified URL, domain, or site section. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Returns a list of a site's or URL's best-performing pages, ranked by the number of referring external links, with flexible filtering and sorting options. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves a site's or page's internal link metrics, allowing analysis of how pages within the given domain or URL are interconnected and which pages receive the most internal links. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Returns the distribution of pages by estimated organic traffic buckets for a specified domain or URL, across all locations or for a specified country. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves historical data about pages from a specified domain, URL, or section of a site, grouped by a chosen time interval. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Returns detailed metrics about pages on a specified site or URL that are ranking in paid search results, including traffic, keyword data, ad presence, and changes over time, with powerful filtering and comparison capabilities. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Provides historical data on referring domains linking to a specified target (domain or URL) over a defined date range, with customizable grouping and analysis scope. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves detailed information about referring domains that link to a specified target domain or URL, with flexible filtering, selection, and sorting of backlink-related metrics. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Returns a list of the top-performing pages for a specified website or URL, including detailed SEO metrics (such as organic rankings, traffic, top keyword, and changes over time), with support for comparison between two dates and flexible filtering. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Returns historical totals of search volume for keywords that the specified domain or URL ranks for in the top 10 or top 100 results, across all countries or for a specified country. When analyzing a domain name, you must use mode=subdomains. Using mode=domain can exclude www and other subdomains. Use doc tool first to get the real input schema.

Retrieves the historical URL rating data for a specified domain or URL over a defined date range, grouped by a chosen time interval. Use doc tool first to get the real input schema.

Idempotent endpoint to create or update a GitHub-backed skill. Send application/json with `gitUrl`.

Start a database export for a cluster. Asynchronous: poll skycloak_get_export until the status is 'completed' to obtain the download URL. Including credentials requires an encryption_password.

Get a presigned URL to upload a realm archive to. PUT the archive to upload_url, then pass the returned s3_key to skycloak_create_realm_import as upload_s3_key. Not needed when importing an existing export: pass that export's ID as source_export_id instead.

Get a database export job by ID, including its status, progress, and (once completed) the time-limited download URL.

Get a realm export job by ID. Poll this after skycloak_create_realm_export until status is 'completed'; the download URL only appears then and expires 24 hours later.

Get a permanent URL for a specific message.

List all custom emoji in the workspace. Returns emoji name-to-URL mapping. Aliases use "alias:emoji_name" format.

Upload a text file to Slack. Uses the 2-step upload process (getUploadURLExternal + completeUploadExternal). For text/code content only.

Attempt to log in to a website. Navigates to the login URL, finds email/username and password fields, fills them in, and submits the form with click, Enter, and form-submit fallbacks for Clerk and other multi-step auth UIs. Returns a screenshot and reports whether login succeeded, failed, or needs verification. Always ask the user for credentials first — never guess. If the site requires email verification (OTP code), use read_verification_email to automatically fetch the code from Gmail (requires one-time authorize_email_access setup).

Spends one researched cluster from the plan. Researches a topic deeply into a durable dossier: four search engines are each asked their own questions, the best sources found are fetched and read, and the claims extracted from them are merged into one list with source URLs, dates, the points where sources disagree, and the questions the research could not settle. Runs as a background job — poll get_research_dossier or wait_for. Research a topical cluster once and let its articles draw different subsets; researching per article costs more and is what makes articles in one cluster sound alike. Pass planId + workstreamId to research a workstream (its title, goal, audience and brand keywords are used automatically, and the workstream's existing dossier is reused), or topic for a free-form one. A workstream-bound run also proposes articles from the dossier when it finishes.

Build a read-only maintainer-reviewed HeyClaude submission draft with canonical PR text and URLs.

Build prefilled HeyClaude submit and review URLs for a validated PR-first submission draft without making write calls.

Validate and persist core onboarding artifacts for a product/session. Prerequisites: - prompt pack must be acknowledged for `session_id` - payloads should match the artifact schemas below Common use: - called by `run_full_agentic_onboarding` - can also be used for staged/recovery runs Expected formats: - market_position: patch object with market position keys - conversion_notes: {'Product Name','Payment Terms/Plans','General Notes'} - funnels: [{'url','description','primary_use_case', optional 'qualification'}]