Crawlgraph MCP server
Backlink lookups and competitor gap analysis on Common Crawl's open web graph (4.4B links).
6 stars
Reviews
Write oneNobody has reviewed Crawlgraph yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Crawlgraph tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- –Code scanpackage could not be scannedn/a
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 14 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
What the publisher says
From the Crawlgraph repository's README, as published. We do not edit it. Read it on GitHub
crawlgraph-mcp
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).
Backlink data without the $129/month subscription. CrawlGraph is $99 lifetime; API access is included on the lifetime tier.
What you can do
- backlinks — every referring domain for a target, with authority scores
- gapanalysis** — domains linking to your competitors but not to you
- gapoutreachtargets — the warm-outreach play: the domains that link to all of your competitors but not to you, ranked and de-noised. These are publishers who cover your whole space and have simply never heard of you — the warmest backlink targets you will ever pitch.
- backlinkchanges** — additions, observed absences, and authority movement between Common Crawl snapshots
- releases — list the Common Crawl snapshots you can query
Install
You need a CrawlGraph API key (cglive...). Free tier: 15 backlink calls/month, no card - get a key emailed to you at crawlgraph.com/docs/api. The gapanalysis and gapoutreach_targets tools need the $99 lifetime tier (1,000 calls + 50 gap analyses/month, no subscription).
Claude Desktop / Claude Code
Add to your MCP config (claudedesktopconfig.json, or .mcp.json for Claude Code):
{
"mcpServers": {
"crawlgraph": {
"command": "npx",
"args": ["-y", "crawlgraph-mcp"],
"env": {
"CRAWLGRAPH_API_KEY": "cg_live_your_key_here"
}
}
}
}Cursor / Windsurf / Cline / Zed
Same shape — point the client's MCP config at npx -y crawlgraph-mcp with CRAWLGRAPHAPIKEY in the env. Restart the client and the five tools appear.
Hosted endpoint
Clients that support Streamable HTTP can use the zero-install hosted endpoint at https://crawlgraph.com/mcp with the same bearer key. This package's local 0.3.0 server exposes the five tools above; hosted package versions are released separately and must be verified with tools/list before relying on the new backlink_changes tool. See the hosted MCP smoke runbook for the operator-owned release and verification process.
The outreach play, in one prompt
Once it's connected, you don't call the tools by hand — you describe the goal:
"Use gapoutreachtargets for mydomain.com against competitor-a.com and competitor-b.com, then draft a short, specific outreach email to each priority target."
Behind the scenes the server submits the gap job, polls until it completes, filters the results down to the domains that link to every competitor but not to you, strips out platform/CDN noise (amazonaws, github, facebook, ...), and hands your agent a clean ranked list to write outreach against.
Why 2-3 competitors, not one: a site linking to one competitor might be a fluke or a paid placement. A site linking to three of your competitors is a publisher who covers your whole category. That overlap is the qualifier.
Tools reference
Lifetime quota: 1,000 backlinks calls + 50 gap jobs per calendar month. Full API reference: crawlgraph.com/docs/api.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Install directly
The registry entry has no remote endpoint or installable package.
Crawlgraph: common questions
- Is Crawlgraph MCP server safe?
- Mostly: it is graded B (73/100). Read the Crawlgraph safety report
- Does Crawlgraph need an API key?
- Yes. The registry entry asks for
CRAWLGRAPH_API_KEY. - Is Crawlgraph maintained?
- The last commit was 15 days ago (2026-09-12). The latest release is v0.2.2.
- What can I use instead of Crawlgraph?
- Servers from other publishers that do the same job: Web Validator by DigestSEO MCP server, Sonar MCP server and Visibly AI — SEO MCP Server. Compare all Crawlgraph alternatives.
Alternatives to Crawlgraph
Same job from other publishers: the closest match first, then the best rated.
Web Validator by DigestSEOAudit public webpages and supplied markup for HTML, CSS, SEO, JSON-LD, and link issues.not reviewedGrowingA- SonarASO tools for AI agents: keyword research, rank tracking, competitor analysis (iOS & Android).not reviewedGrowingA
Visibly AI — SEO MCP ServerRemote SEO/GEO MCP: Search Console, keyword research, backlinks, competitor & on-page audits.not reviewedGrowingA- Web Intel (x402)Pay-per-call web extraction, SEO audits and text analysis. USDC on Base via x402, no API keys.not reviewedGrowingA
- Nimrod ResearchWeb research for agents: quality-scored Google search, webpage extraction, and deep research.not reviewedGrowingA