MCP SERVERLook up a domain's referring domains, and find the sites that link to your competitors but not to you.
LABSCO SUMMARY
gap_outreach_targets is the one to reach for: it runs the gap job, keeps only the domains linking to every competitor you named, strips platform noise, and ranks what is left. The data is a quarterly Common Crawl snapshot, so it fits one-off prospecting rather than watching links change day to day.
A server over the CrawlGraph backlink API, which is built on the public Common Crawl webgraph. Four tools: backlinks for one domain, a competitor gap analysis, a ranked outreach list, and the crawl snapshots you can query.
A CrawlGraph API key, handed to the server at launch. The free tier covers backlink lookups; the two gap tools sit on the paid lifetime tier. Runs under Node.
One command plus a key — npx -y crawlgraph-mcp, then supply credentials
USE CASES
Name two or three competitors and get back the domains linking to all of them but not to you, de-noised and ranked by authority.
Pull every referring domain with its authority score, plus the target's own authority and rank.
Run the gap first for the shortlist, then score one specific domain on its own.
List the available snapshots and pin the lookup to the one you want.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
backlinksLook up referring domains (backlinks) for a single target domain from the Common Crawl webgraph. Returns each linking domain with host count and CrawlGraph authority score, plus the target's own authority/rank. Costs one backlinks call against the monthly quota (1,000/mo on lifetime).
gap_analysisRun a competitor backlink gap analysis: find domains that link to one or more of your competitors but NOT to you. Submits an async job and polls until done (usually 5-30s). Returns every gap with found_on listing which competitors each domain links to. Costs one gap job against the monthly quota (50/mo on lifetime).
gap_outreach_targetsThe warm-outreach play. Runs a gap analysis, then ranks results: PRIORITY = domains linking to ALL your competitors but not you (publishers who cover your whole space and have never heard of you), SECONDARY = domains linking to 2+ competitors. Platform/CDN noise is filtered, top N priority targets are scored by authority. Use 2-3 competitors. Costs one gap job + one backlinks call per enriched target.
releasesList the Common Crawl releases the API can query. Does not count against any quota. Use a release id with the backlinks tool to query a specific snapshot.
BEFORE YOU INSTALL
4 tools when we connected. gap_analysis and gap_outreach_targets need the paid lifetime plan; the free tier gives 15 backlinks calls a month. Data comes from a quarterly Common Crawl snapshot, not a live crawler.
Both documented clients run the server on your machine.
CONTEXT COST
Rated by the size of the 4 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx -y crawlgraph-mcp{
"mcpServers": {
"crawlgraph": {
"command": "npx",
"args": [
"-y",
"crawlgraph-mcp"
],
"env": {
"CRAWLGRAPH_API_KEY": "<YOUR_CRAWLGRAPH_API_KEY>"
}
}
}
}MCP servers
ezbiz-services
GiorgiKemo
rampify-dev
djeknet