MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Free, open-source on-page SEO audit: web app, JSON API, CLI, TUI and MCP server. https://seo.rank
MIT -
@mangerik/wordpress-mcpgithub.com/mangerik/wordpress-mcpupdated this year
MCP Server for WordPress REST API — connect AI agents to WordPress (posts, pages, media, users, custom post types, WooCommerce, Yoast / Rank Math, block themes, multisite, batch).
npm MIT -
mcp-gsc-advancedgithub.com/arturseo-geo/mcp-gsc-advancedupdated this year
MCP server for advanced Google Search Console — keyword cannibalization detection, page-level query deep dive, crawl+GSC gap analysis, rank change alerts. Extends basic GSC beyond any existing MCP. By TheGEOLab.net
NOASSERTION -
wp-seo-meta-bridgegithub.com/Mrshahidali420/wp-seo-meta-bridgeupdated this year
Detects your active SEO plugin (Rank Math / Yoast / SEOPress) and exposes its fields to the WordPress REST API, so the block editor and MCP agents can set SEO while building pages.
GPL-2.0 -
Cursor SEO MCP — open-source SEO MCP server for Cursor. AEO, GEO, technical SEO, on-page audits. Evidence JSON, never invented rankings.
pypi MIT -
Revenue-weighted SEO MCP server for content creators. Connects Google Search Console to page content and ranks opportunities by money, not clicks.
pypi ★ 2 -
Serpex MCP server: web search API and extract API for AI agents. Ranked web results, optionally with page content as markdown, and page extraction
npm MIT -
Free, unlimited API for the world's top trending news. Clusters stories across 50+ outlets and Google News, ranks what's trending. Free hosted JSON on GitHub Pages, self-hostable, NewsAPI.org-compatible, MCP server.
MIT ★ 3 -
SEO content planning plugin for Codex & Claude Code: give it your website and goal, get the pages to create or update and what to write that ranking pages miss — backed by DataForSEO data and real page reading.
MIT -
competitive-intel-mcpgithub.com/danishashko/competitive-intel-mcpupdated this year
Competitive Intelligence MCP Server — track competitors, monitor SERP rankings, scrape pages, and build knowledge graphs
npm MIT -
Safely connect Google Search Console to Grok, Grok Bot and Cursor, so your agent can check rankings and clicks, find pages losing traffic, explain why a page isn't indexed and, on a paid plan, submit the sitemaps you approve.
MIT -
Fast, low-token web reader and focused crawler for AI assistants, served over MCP. Returns ranked passages instead of whole pages.
cargo Apache-2.0 ★ 7 -
mcp-search-servergithub.com/ZhenMoon/mcp-search-serverupdated this year
多引擎聚合搜索本地 MCP 服务器 — 8 引擎并行 + 去重排序 + 网页正文提取 + 深度研究。 Local multi-engine aggregated search MCP server — 8 engines parallel + dedup/ranking + page fetch + deep research.
MIT ★ 1 -
MCP server for the Anchor SEO platform — GSC Page Indexing history, Screaming Frog crawl data, and ranked technical-SEO audits for Claude and other MCP clients.
npm UNLICENSED -
MCP server for Appsurify TestMap — exposes test-coverage analytics (context resolution, ranked coverage gaps, element context, zero-coverage pages) to AI agents.
npm MIT -
The focused-crawling MCP server for AI agents. Rank a whole site by your topic, read any page as clean Markdown, extract anything
pypi MIT ★ 12 -
deepseek-search-fetch-mcpactive
MCP server for the DeepSeek Search and Fetch APIs: ranked web search and page-to-Markdown fetch for Claude Code and any MCP client.
npm MIT -
RAG engine for whole websites: async multi-page scraping with JS rendering, hybrid semantic + TF-IDF ranking on FAISS, LLM answers, and an MCP server so AI agents can query it.
-
WordPress MCP server and CLI for Claude Code and AI agents. 42 tools for posts, pages, custom post types, media, taxonomies, users and comments over the WordPress REST API, plus Elementor page data, Rank Math SEO, redirects and bulk edits through an optional helper plugin. Multi-site.
npm MIT -
Web research for AI agents in one tool call: search → read the full pages → rank → cited passages. Library, MCP server and CLI; zero API keys needed.
npm MIT ★ 1 -
Self-hostable SEO platform: technical crawler, on-page optimisation, keyword research and rank tracking, white-label reporting. FastAPI REST API + MCP server + Next.js dashboard. Runs fully offline on mock providers.
MIT -
Ask questions about your PDFs and get answers with page-level citations. Hybrid FAISS + BM25 retrieval with Reciprocal Rank Fusion, LLM-judged evaluation (18/20 correctness, 20/20 faithfulness) and an MCP server for AI clients.
MIT ★ 1 -
Web search, page reading and browser automation for Python and AI agents. Search Brave, DuckDuckGo, Yahoo, Mojeek, Google and Bing with no API key, read pages as clean Markdown, and give both to agents as OpenAI, Anthropic, LangChain, LlamaIndex or CrewAI tools, or over MCP. Browser TLS impersonation, consensus ranking, honest block detection, caching, Selenium and Playwright.
pypi MIT -
DocShark is a powerful MCP server buit with TMCP, designed to scrape, index, and search any documentation website. It creates a local, highly-searchable knowledge base from public documentation pages using FTS5 (Full-Text Search) and BM25 ranking, allowing AI assistants to query the latest docs effortlessly.
npm MIT ★ 2 -
The Brave Search API as a CLI and local MCP server — ranked web results, page text pre-extracted to a token budget for grounding a model, and cited answers from one search or a multi-step research run. Every result prints its cost; nothing is cached (Brave ToS)
MIT -
Bulk AI CLI Connector: connect Claude, ChatGPT and MCP agents to WordPress. Bulk edit Yoast and Rank Math SEO meta, JSON-LD schema, redirects and Elementor or Beaver Builder page copy over the REST API, with undo. Free WordPress.org plugin with a bundled MCP server.
GPL-2.0 ★ 5 -
SEO Performanceno update data
Post-publish SEO performance MCP. Unifies **Google Search Console, Matomo, GA4, Microsoft Clarity, and AI-citation signals** per URL and emits a **verdict per post** (refresh / expand / merge / kill / double_down / hold) with deterministic reason codes and a 0-1 confidence score. Reporting only — never mutates posts. Works with any CMS via XML sitemap; optional Ghost Admin API integration for richer metadata. ## Tools - **posts.list** — discover posts via XML sitemap, JSON override, Ghost Admin API, or explicit URL list. - **posts.snapshot** — unified 30/60/90-day signal pull across every configured source for one URL. - **posts.decay_curve** — weekly GSC bucket + decay / plateau / growth classification. - **posts.verdict** — rule-based verdict engine: refresh, expand, merge, kill, double_down, hold. - **posts.refresh_brief** — markdown brief: verdict + reasons + numbers + suggested actions. - **posts.cite_loss** — list of LLMs that previously cited this URL but no longer do. - **cohort.report** — verdict engine across a cohort, ranked by verdict priority + confidence. - **gsc.quick_wins** — pages at positions 5-15 with low CTR, ranked by impressions. ## Prompts - **audit_cohort** — run cohort.report and generate refresh briefs for every actionable URL. - **find_quick_wins** — propose query-verbatim title and H1 rewrites for SERP underperformers. - **citation_loss_sweep** — find URLs that lost LLM citations and recover them. ## How it works Each source is best-effort: if its env vars are missing the field is omitted. Returns whatever is available. Optional DuckDB cache layer for historical comparisons. Platform-agnostic — works with WordPress, Hugo, Astro, Next.js, Webflow, Framer, Wix, Squarespace, Substack, Ghost, and any CMS that exposes a sitemap.
smithery -
@noleemits/vision-builder-mcpgithub.com/noleemits/vision-builder-mcpupdated this year
MCP Server for Noleemits Vision Builder - Connect Claude Desktop to WordPress + Elementor. Manage pages, sections, content, and SEO via AI.
npm GPL-2.0-or-later -
Blazingly fast, local-first website crawler and 120-rule technical SEO audit engine with native MCP support.
Apache-2.0 ★ 6 -
MCP server giving Claude Code, Cursor & Codex permanent AST code memory. 98.9% token reduction. 100% local.
pypi Apache-2.0 ★ 6 -
rankoraclegithub.com/ToolOracle/rankoracleupdated this year
RankOracle — AI-Native SEO Intelligence MCP Server. 13 tools for keyword research, SERP analysis, domain audits, competitor gaps, on-page optimization. First standalone SEO MCP.
MIT