Cygnix SEO

io.github.cygnixlabs-cmdPublished by GitHub account cygnixlabs-cmdv1.0.0Updated Nov 4, 2026

No-API-key SEO tools: keyword clustering, search intent, cannibalization, meta checks, briefs.

VerifiedSTDIODesktop onlyData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Local, no-API-key SEO toolkit that lets an assistant cluster keywords, classify search intent, find cannibalization, check titles and metas, and draft content…

What you can do
  • Cluster a keyword list into topical clusters with a pillar keyword per cluster
  • Label keywords by search intent (informational, commercial, transactional, navigational)
  • Read a Google Search Console query-plus-page CSV and flag queries where pages compete, ranked with a suggested fix
  • Score title tags and meta descriptions for length, truncation, keyword placement and CTR hooks
  • Build a content brief with intent, title options, meta draft, slug, H2 outline and checklist
When to use it
Useful when you are doing keyword research, on-page SEO review or content planning and want a fast, deterministic first pass on your own keyword lists, titles or Search Console exports without signing up for an SEO platform.
Requirements
Node.js 18 or later; runs as a local stdio process, typically launched with npx. No accounts, API keys, environment variables or headers are declared. Cannibalization checks need a Search Console export where each row is a query-page pair.
Before you install
Tools are rule-based and lexical, and title pixel widths are approximations, so results should be confirmed against live search results. No search volume or difficulty estimates are produced. The README also points to separate paid cloud tools on Apify and paid skill packs; those are not part of this local server and cost money per result.

Installation

In SourceWeft

  1. Open Cygnix SEO in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Cygnix SEO MCP: free SEO tools for Claude, Cursor & any MCP client

[npm] [License: MIT]

5 no-API-key SEO tools that work on your data: paste keywords, a Google Search Console export or your titles, and get clusters, intent, cannibalization fixes, CTR checks and content briefs. Everything is deterministic and runs locally. No accounts, no tracking, and no made-up search volumes.

Built by Cygnix Labs.

ToolWhat it does
cluster_keywordsGroups a keyword list into topical clusters and picks a pillar keyword per cluster (one cluster ≈ one page)
classify_search_intentLabels keywords informational / commercial / transactional / navigational, with the matching signal
find_keyword_cannibalizationReads GSC CSV (Query + Page) and flags queries where your own pages compete, ranked HIGH/MEDIUM/LOW, with a fix
check_title_metaScores title tags and meta descriptions (0–100): char + pixel truncation, keyword placement, CTR hooks
content_brief_outlineBuilds a brief from your keyword: intent, title options, meta draft, slug, H2 outline, questions to answer, on-page checklist

Install

Requires Node.js 18+.

Claude Desktop

Edit claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):

json
{  "mcpServers": {    "cygnix-seo": { "command": "npx", "args": ["-y", "cygnix-seo-mcp"] }  }}

Restart Claude Desktop.

Cursor

Settings → MCP → Add new server, or add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

json
{  "mcpServers": {    "cygnix-seo": { "command": "npx", "args": ["-y", "cygnix-seo-mcp"] }  }}

Claude Code

bash
claude mcp add cygnix-seo -- npx -y cygnix-seo-mcp

Other clients (VS Code, Windsurf, Cline, Zed…)

Any MCP client that supports stdio: command npx, args -y cygnix-seo-mcp.

From source

bash
git clone https://github.com/cygnixlabs-cmd/cygnix-seo-mcp && cd cygnix-seo-mcpnpm install && npm testnode dist/index.js

Example prompts

  • "Cluster these 80 keywords and tell me which page each cluster should target:" (paste list)
  • "Classify the search intent of these keywords and flag the commercial ones."
  • "Here is my GSC export (query + page). Find keyword cannibalization and tell me what to merge."
  • "Check the titles and meta descriptions for these 10 URLs against their target keywords."
  • "Write a content brief for 'technical seo audit' using these related keywords: …"

Example output (cannibalization)

## [HIGH] "seo audit checklist" (2 pages, #2 page share 38%)| Page | Clicks | Impr | Avg pos || https://site.com/a | 30 | 1000 | 4.2 || https://site.com/b | 5 | 600 | 9.1 |Action: Pick https://site.com/a as canonical target; merge/301 or de-optimize the others...

GSC input contract (cannibalization): each CSV row must be one query–page pair, with columns for query, page, clicks, impressions and position (header names are matched loosely). Separate Queries-only and Pages-only aggregate exports cannot be joined to recover those pairs. Example file: gsc-query-page.csv.

How to get that export:

  • Prefer Looker Studio or the Search Console API, which can export query + page together.
  • In the Search Console UI, dimensions are one at a time (Google’s filtering docs; export docs). Manual route for selected-query coverage (not a full site-wide export): open Performance → Search results → click one query to filter → switch the dimension to Pages → Export → add that exact query as a column on every row. Repeat for the queries you care about, keep date/search-type filters the same, and append the rows.

More Cygnix SEO tools

Free agent skills (npx skills add cygnixlabs-cmd/cygnix-seo-skills), pay-per-use Apify actors for full-site SEO + AEO/GEO audits, and the rest of the toolkit: Cygnix Labs tool directory.

Honest limits

  • Intent and clustering are rule-based/lexical, so treat them as a fast first pass and confirm with the live SERP.
  • Title pixel widths are approximations of Google's SERP rendering.
  • No tool estimates search volume or difficulty. Use your own data source for that.

Paid pro tools

Need more than the free tools? These run in the cloud on Apify. You pay per result, and Claude, ChatGPT and Cursor agents can call them through the Apify MCP server:

ToolWhat it doesPrice
AEO & AI Search Readiness CheckerScores pages 0-100 for ChatGPT, Perplexity and AI Overviews: schema, answer-first content, FAQ, llms.txt, GPTBot/ClaudeBot access5 pages/run free, then $0.005 / page ($5 / 1,000)
SERP Intent MapperSearch intent + page type for every keyword100 keywords/run free, then $0.50 / 1,000
Keyword Clusterer + Content BriefTopic clusters, pillar keywords, content briefs100 keywords/run free, then $0.70 / 1,000 + $0.01 / brief
Keyword Cannibalization FinderPages competing for the same query, from a GSC export5 issues/run free, then $0.005 / issue
Content Decay AuditPages losing Google traffic, ranked by clicks lost, with refresh plans25 pages/run free, then $1 / 1,000 pages

Prices checked 2026-10-29 against each Actor's live Apify Store pricing page (e.g. Keyword Cannibalization Finder pricing) and the public Apify API (api.apify.com/v2/acts/cygnix_labs~<actor>). The Apify Store page is the source of truth if they ever differ.

Full agent skills (Claude Code / Cursor SKILL.md packs): Cygnix Labs on Agensi

Want the full workflow?

These tools are the free starter layer of the Cygnix SEO Toolkit: full agent skills, prompts and sheets for keyword research → briefs → audits → content refresh.

Keywords

MCP server, Model Context Protocol, SEO MCP, keyword research, keyword clustering, search intent classifier, keyword cannibalization, Google Search Console, title tag checker, meta description length, CTR optimization, content brief generator, Claude SEO, Cursor SEO, AI SEO tools, free SEO tools, no API key.

License

MIT © Cygnix Labs

Source: README.md at commit ec1a6af

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestOct 14, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts