The MCP tool directory.

List the domains for a server.

Update the managed run.tools slug for a server.

Retrieve server details including connections, tools, and security status.

Search and browse public MCP servers in the Smithery registry. Supports full-text and semantic search via the `q` parameter, and filtering by deployment status, verification, ownership, and more.

Retrieve release details including status, git metadata, pipeline logs, and MCP endpoint URL.

List releases ordered by most recent first. Logs are omitted — fetch a specific release to see logs.

Resume a paused release (e.g. after OAuth authorization). Use id='latest' to resume the most recent one.

Submit a release via multipart form. Supports hosted (JS module upload), external (URL), and stdio (MCPB bundle) release types.

Partially update the GitHub repository connection settings. Only provided fields are updated.

Remove the GitHub repository connection.

Get the connected GitHub repository, if one exists.

Create or update the GitHub repository connection. Idempotent — updates if a connection already exists.

Remove a secret by name.

List secret names. Values are not returned.

Create or update a secret value.

Create a new server. Idempotent — returns success if the server already exists and is owned by the caller.

Create an API key for your StacksFinder account. For ChatGPT OAuth users: pass any value for email/password (e.g., "[email protected]" / "oauth") - they are ignored when OAuth is active. Requires Pro or Team tier.

Preflight check for MCP -> onboard_api connectivity and auth context. Use this first in a new session to confirm: - backend is reachable - current MCP session auth state - whether a default client id is configured

List active sessions + blocking locks. Uses the dialect's own system view — `pg_stat_activity` on postgres, `information_schema.processlist` on mysql, `sys.dm_exec_requests` joined with `sys.dm_tran_locks` on mssql. No dialect arg needed — inferred from the connection. **Required privileges (per dialect):** postgres — `pg_read_all_stats` role membership (or be the role that owns the queries; otherwise you only see your own session); mysql — `PROCESS` privilege; mssql — `VIEW SERVER STATE`. If the role lacks the privilege the tool returns a clean `Query blocked by security policy` error rather than partial data — grant the role above and retry. RDS/Aurora/Azure managed PostgreSQL: `pg_read_all_stats` is grantable but not on by default. [BUILD tier]

Get a law article with legal terms replaced by everyday Korean (쉬운 법률 읽기). Fetches a law article and annotates legal jargon with plain Korean equivalents using the official 법제처 legal terminology database. Args: law_name: Law name (e.g., "민법", "근로기준법") article: Article number (e.g., 750 for 제750조) article_branch: Branch number (e.g., 2 for 제37조의2, default 0) oc: Optional OC override type: Response format - "JSON" (default), "XML", or "HTML" Returns: Original text, simplified text with inline annotations, and term glossary Examples: >>> simplify_article(law_name="민법", article=750) >>> simplify_article(law_name="건축법", article=37, article_branch=2)

Returns all issues from your Site Audit crawl. By default, it provides data from the latest available crawl, but you can also specify a crawl date and time to retrieve historical metrics. Use doc tool first to get the real input schema.

Returns the HTML and extracted text content of a page from your Site Audit crawl. By default, it provides the latest available snapshot, but you can also specify a crawl date and time to retrieve historical snapshots. You can choose to pull raw HTML, rendered HTML, or page text. The endpoint is available only for projects with verified ownership. Use doc tool first to get the real input schema.

Returns detailed information about pages discovered in a Site Audit project, including URLs, crawl metadata, and selected on-page metrics. Use doc tool first to get the real input schema.

Returns Site Audit project summaries (all projects or a specific project), including health scores, issue counts, and crawled page counts for the latest crawl or a specified historical point in time. Use doc tool first to get the real input schema.

Retrieves detailed information about all backlinks pointing to a specified URL or domain, with extensive filtering, sorting, selection, and aggregation 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 anchor text and associated backlink metrics for a specified domain or URL, with filtering and selection 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.

Provides backlink statistics for a specified URL or domain as of a given date, with options to control protocol and 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 a list of broken backlinks (i.e., links pointing to non-functioning pages) for a specified domain or URL, with customizable filtering, field selection, and aggregation 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 the domain rating and related metrics for a specified domain or URL as of a specific date. Use doc tool first to get the real input schema.

Retrieves the historical domain rating data for a specified domain or URL over a defined date range and grouping interval. Use doc tool first to get the real input schema.