{
  "markdown": "# mcp-semrush\n\nSemrush MCP Pack — SEO analytics via the Semrush Analytics API.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `domain_overview` | Domain overview (Semrush type=domain_ranks): high-level SEO/PPC summary for a domain. Returns parsed rows with columns: Db (database), Dn (domain), Rk (Semrush rank), Or (organic keywords count), Ot (organic traffic), Oc (organic traffic cost), Ad (adwords/paid keywords count), At (paid traffic), Ac (paid traffic cost). Consumes your Semrush API units. |\n| `domain_organic_keywords` | Top organic search keywords a domain ranks for (Semrush type=domain_organic). Returns parsed rows with columns: Ph (keyword phrase), Po (current position), Pp (previous position), Nq (search volume), Cp (CPC), Ur (ranking URL), Tr (traffic %), Co (competition), Nr (number of results). Consumes your Semrush API units. |\n| `domain_paid_keywords` | Paid (AdWords/PPC) keywords a domain bids on (Semrush type=domain_adwords). Returns parsed rows with columns: Ph (keyword phrase), Po (ad position), Nq (search volume), Cp (CPC), Ur (landing page URL), Tg (traffic), Tc (traffic cost), Co (competition), Nr (number of results). Consumes your Semrush API units. |\n| `keyword_overview` | Keyword overview (Semrush type=phrase_this): search metrics for a single keyword phrase. Returns parsed rows with columns: Ph (phrase), Nq (search volume), Cp (CPC), Co (competition 0-1), Nr (number of organic results), Td (trend, last 12 months as \\|-separated values). Consumes your Semrush API units. |\n| `backlinks_overview` | Backlinks summary for a domain or URL (Semrush type=backlinks_overview). Returns parsed rows with columns: target, target_type, total (total backlinks), domains_num (referring domains), urls_num (referring URLs), ips_num (referring IPs), follows_num (dofollow), nofollows_num, texts_num, images_num, score (authority score). Note: backlinks reports are not regional — there is no `database` param. Consumes your Semrush API units. |\n| `organic_competitors` | Organic search competitors for a domain (Semrush type=domain_organic_organic). Returns parsed rows with columns: Dn (competitor domain), Cr (competition level), Np (common keywords), Or (competitor organic keywords), Ot (competitor organic traffic), Oc (organic cost). Consumes your Semrush API units. |\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"semrush\": {\n      \"url\": \"https://gateway.pipeworx.io/semrush/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/semrush/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Semrush data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 4458,
  "sha": "cf96838830823f8f7c5c0ede53998a7c4bbaf2ca60118acd411e0b13fd5f8520",
  "repo_slug": "pipeworx-io/mcp-semrush",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_semrush_5bd041c3/readme"
}