mcp-common-crawl
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| discover_backlinksA | Discover backlinks to a domain using Common Crawl CDX API (3 indexes). Returns source URLs, anchor text, link context. Free alternative to Ahrefs/Semrush backlink API. |
| find_expiredA | Find expired or parked domains in a niche using Common Crawl. Searches CC CDX for domains matching keywords, checks liveness. Returns domain status (expired/parked/live). |
| check_domainA | Deep check a single domain — liveness, parked page detection, Common Crawl page count, last seen date. |
| competitor_gapA | Find domains linking to competitors but not to you. Queries Common Crawl for backlinks to each competitor, diffs against your domain. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Tools have distinct purposes, but discover_backlinks and competitor_gap both involve backlink queries, while find_expired and check_domain both assess domain status. Descriptions clarify the differences, so ambiguity is low but not zero.
Naming is inconsistent: discover_backlinks and check_domain use verb_noun, find_expired uses verb_adjective, and competitor_gap is a noun phrase. All use lowercase underscores, but the patterns are mixed.
Four tools is well-scoped for a Common Crawl domain analysis server. Each tool addresses a distinct task without redundancy, and the count fits the niche purpose perfectly.
The surface covers core domain-backlink workflows: backlink discovery, expired domain hunting, domain status checks, and competitor gap analysis. A general URL search or content fetch tool is missing, but agents can work around it.