Skip to main content
Glama

backlink-mcp

Full docs & install guide → sellonllm.com/backlink-mcp.html

Automate backlink research, unlinked mention hunting, and outreach prep inside your AI assistant. Free, no API keys required.

Connect to Claude, Cursor, or any MCP-compatible AI assistant and let it find backlink opportunities, discover unlinked mentions, research prospects, and extract contact info for outreach — all for free.

Part of the SellOnLLM SEO MCP suite — a hub of free MCP servers for SEO and AI visibility.


Why this exists

Tools like Ahrefs and Moz cost hundreds of dollars a month. This MCP gives you backlink research capabilities directly inside your AI assistant at zero cost, using:

  • DuckDuckGo — mention discovery and prospect finding

  • Wayback Machine CDX API — historical link data

  • httpx + BeautifulSoup — page scraping and link verification


Related MCP server: crawlgraph-mcp

Tools

Tool

Description

find_mentions

Find all pages mentioning your domain (linked or unlinked)

find_prospects

Discover guest post, resource page, and roundup opportunities by niche

find_competitor_link_sources

Find pages linking to a competitor — prime outreach targets

verify_page_links

Scrape a URL to check if it links to you and extract contact info

extract_contact_info

Pull emails, social handles, and contact pages from any site

check_page_history

Check Wayback Machine history — verify a page still exists


Quickstart

1. Clone and install

git clone https://github.com/vipul510-web/mcp-backlink-for-seo.git
cd mcp-backlink-for-seo
python3 -m venv .venv
.venv/bin/pip install "mcp[cli]>=1.0.0" "ddgs>=9.0.0" httpx beautifulsoup4 lxml

2. Connect to Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "backlink-mcp": {
      "command": "/absolute/path/to/backlink-mcp/.venv/bin/python",
      "args": ["/absolute/path/to/backlink-mcp/server.py"]
    }
  }
}

Restart Claude Desktop. The backlink tools will appear automatically.

3. Connect to Cursor

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project):

{
  "mcpServers": {
    "backlink-mcp": {
      "command": "/absolute/path/to/backlink-mcp/.venv/bin/python",
      "args": ["/absolute/path/to/backlink-mcp/server.py"]
    }
  }
}

4. Connect to any MCP-compatible client

.venv/bin/python server.py

The server communicates over stdio, compatible with any MCP client.


Usage examples

Once connected, just talk to your AI assistant:

Find unlinked mentions (outreach opportunities):

Find unlinked mentions of mybrand.com

Discover guest post opportunities:

Find guest post opportunities in the personal finance niche

Research a competitor's backlinks:

Who links to competitor.com? Find me 20 results.

Verify and enrich a prospect:

Check if techblog.com/article links to mybrand.com and find their contact email

Full link building workflow:

1. Find prospects in the SaaS marketing niche
2. Verify which ones don't already link to mysaas.com
3. Extract contact info for the top 5
4. Draft an outreach email for each

Typical workflow

find_prospects / find_mentions / find_competitor_link_sources
                    ↓
              verify_page_links
          (linked or unlinked? contact info?)
                    ↓
           extract_contact_info
              (email, socials)
                    ↓
          outreach via Gmail MCP

Requirements

  • Python 3.10+

  • No API keys needed

  • No paid subscriptions


Limitations

  • DuckDuckGo returns a sample of results, not a complete link graph

  • Rate limiting: built-in 1.5s delay between searches to avoid blocks

  • The Wayback CDX endpoint can occasionally return 503 or time out; check_page_history retries automatically

  • Common Crawl graph data (full inbound link index) is not yet integrated — contributions welcome

Changelog (recent)

  • 0.1.1 — Switched search from deprecated duckduckgo-search to the maintained ddgs package (same DuckDuckGo backend; fixes empty search results). Hardened Wayback CDX with HTTPS, longer timeouts, and retries.


Contributing

PRs welcome. High-impact areas:

  • Common Crawl graph API integration for true inbound link discovery

  • Broken link detection (find dead pages on prospect sites)

  • Bulk processing (run across a list of URLs)

  • Output to CSV / Google Sheets


Part of SellOnLLM

This MCP is part of the SellOnLLM SEO MCP suite — free, open-source MCP servers for SEO and AI visibility built for Claude and Cursor.


License

MIT

Related MCP Connectors

  • Open-source AI SEO over MCP: audits, ranks, keywords, backlinks + AI visibility (GEO).

  • SEO MCP server: crawl your site, find AI-visibility gaps, and ship the fix from your coding agent.

  • Your agent needs the whole search picture — what you rank for, who outranks you, who links to them, what is broken on the site, and whether ChatGPT names you at all. Normally that is three SEO vendors and three subscriptions. **What you can ask for** • "What does this domain rank for, and which competitors take the same keywords?" • "Who links to my competitor and not to me?" • "Crawl this site and list the pages with broken tags or duplicate content." • "Does Perplexity cite us when asked about this category?" • "How hard is this keyword, and what does the SERP look like today?" **How to use it** Point any MCP client at https://mcp.aisa.one/seo/mcp and sign in with OAuth — there is no key to create or paste. 60 tools spanning DataForSEO, Semrush and Ahrefs: SERPs, keywords and difficulty, backlinks and referring domains, on-page crawling, domain authority, and answers from ChatGPT, Claude, Gemini and Perplexity. **Why this rather than the source** Three indexes behind one account, so you can cross-check a number instead of trusting one vendor's version of it. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Check the ranking here, then ask the same agent for that competitor's traffic mix, its ad spend, or the person to email — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** Narrower endpoints: https://mcp.aisa.one/seo-serp/mcp · /seo-keywords/mcp · /seo-backlinks/mcp · /seo-onpage/mcp · /seo-labs/mcp · /seo-ai-visibility/mcp · /seo-content/mcp · /seo-domains/mcp · /seo-business/mcp · /seo-merchant/mcp · /seo-apps/mcp · /seo-serp-other-engines/mcp

  • Your agent needs the link graph — who points at a competitor, what anchor text they use, what was won or lost last month, and which sites link to all of your rivals but not to you. **What you can ask for** • "Who links to my competitor and not to me?" • "What anchors point at this domain, and how spammy are the sources?" • "Which links did this site win and lose in the last 30 days?" • "Compare the referring domains of these five competitors." • "Summarise the backlink profile of these 100 domains in bulk." **How to use it** Point any MCP client at https://mcp.aisa.one/seo-backlinks/mcp and sign in with OAuth — there is no key to create or paste. 27 tools: backlinks and referring domains, anchors, new and lost links over time, domain and page intersections, referring networks, spam scores, bulk summaries for many domains at once, plus Semrush's own backlink and indexed-page sets. **Why this rather than the source** Two independent link indexes behind one account — coverage differs, and the gap is usually the interesting part. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Find the link gap here, then ask the same agent who runs those sites and how to reach them — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo/mcp for all of it at once — rankings, keywords, backlinks, site health and AI-answer visibility across DataForSEO, Semrush and Ahrefs.

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Agent-first SEO toolkit with 24 MCP tools for keyword research, rank tracking, site audits up to 50k pages, competitor analysis, content gap detection, domain reputation, backlink intelligence, Google Search Console integration, and AI-powered strategy generation with Claude, GPT, and Ollama. SQLite-backed and bring-your-own-key.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    MCP server for the CrawlGraph backlink-intelligence API. Gives any MCP client - Claude Desktop, Claude Code, Cursor, Cline, Zed, Windsurf - backlink lookups and competitor gap analysis built on the public Common Crawl webgraph (4.4B edges, 120M domains).
    4
    9 npm
    5
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Open-source technical SEO crawler MCP server built on LibreCrawl. Runs full audits inside Claude, Cursor, or Codex — 50+ checks (hreflang, schema.org, security headers, WAF detection on 200-OK pages), chunked-progressive engine for large sites, ephemeral by design (server forgets every audit after download).
    40
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Google Search Console for Claude, Cursor & any MCP client — one sign-in, 30 seconds, no Google Cloud project. Six read-only tools (search analytics incl. Google Discover, period comparison with computed deltas, batch URL inspection, sitemaps) plus five built-in SEO analyses as slash-commands. Tokens stay on your machine. MIT.
    6
    93 npm
    7
    MIT