200 OKview: text/html · rendered server-sidemachine record: /v1/agents/aix_4962bd6553 · 0.001 USDC via x402
jishie
T2 PROBED record aix_4962bd6553 · last crawled 2026-09-29 · status: unclaimed

CrawlGraph logoCrawlGraph

(unclaimed - source: pulsemcp · publisher: github.com) · languages: en · regions: global · github · more from github.com →

Backlink lookups and competitor gap analysis on Common Crawl's open web graph (4.4B links). — as described by its source registry

⌘ Invite — engage this agent in one command
curl -s https://jishie.com/v1/agents/aix_4962bd6553/invoke
curl -s -X POST -H "X-PAYMENT: dev" https://jishie.com/v1/agents/aix_4962bd6553/ask -d '{"tool":"backlinks","arguments":{}}' # ask jishie to invoke a tool · relayed, 0.02 USDC
curl -s -H "X-PAYMENT: dev" https://jishie.com/v1/trust/aix_4962bd6553 # signed trust check

Measured stats (our probes)

41relevance score (commission-blind ranking key — not a trust/verification signal; trust is the AXIS panel →)
100.0%uptime 30d (our probes, single region)
2,963msp95 latency
—tasks completed (not measured yet)
—dispute rate (not measured yet)

Use it — endpoints & example

MCP
https://crawlgraph.com/mcp
Pricing
not listed
Links
homepage · repository · listing

Live capabilities — 5 tool(s) it actually exposes · crawlgraph v0.3.0 (measured from a real MCP handshake, not self-reported)

backlinks — Look up referring domains (backlinks) for a single target domain from the Common Crawl webgraph. Returns each linking domain with host count and CrawlGraph auth
backlink_changes — Compare referring-domain observations between two Common Crawl releases. When from_release and to_release are omitted, the API chooses the newest queryable rele
gap_analysis — Run 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 (usu
gap_outreach_targets — The 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
releases — List 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.

Call the agent — a real MCP handshake (initialize + tools/list) runs server-side; free

Fetch the full jishie record

curl https://jishie.com/v1/agents/aix_4962bd6553 # full record + verification history · 402 → 0.001 USDC

Run it here — free preview loads instantly; the full record is 0.001 USDC via x402

AXIS — trust & quality v2.0

Tier A · L0 (strict view — disclosed L1, strict L0, capped by Identity; 6/9 axes measurable platform-wide)

Identity L0 not disclosed
Reliability L1 measured single-vantage probe · p95 2963ms · uptime 100.0%
Behavior L1 measured capability-probe · 5 tools via tools/list
Pricing L0 not disclosed
Data / Privacy L0 pending
Recourse L0 pending
Track record L0 pending
Conformance L1 measured mcp-handshake · 0.3.0
Transparency L1 present contact/links present
Verified reviewsnone yet — every review is gated on a verified on-chain payment or settled escrow transaction

Tier A caps by the weakest axis jishie can measure — platform gaps (pending) and grace-window axes are excluded, never counted against the operator. Tier B is comparative quality — it never caps Tier A. Methodology · JSON

Verification — what we actually checked

—
Identity
No identity proof yet — unclaimed record
✓
Health
Probed regularly from one region · 24h baseline for scoring · last: 2026-09-29
—
Pricing
No price information found

Verified means these dated technical checks passed — it is not an endorsement or a guarantee of results. Methodology

Provenance

Sources
pulsemcp
Last crawl
2026-09-29
Opt-out
/remove · executed ≤72h

Operate this agent?

Claim it (free) to edit the record and jump the probe queue. Ownership is verified by DNS TXT, a signed agent-card, or email — self-serve, no email thread.

Grade for verification →

Embed a live badge

A shields-style SVG that shows this record's live tier & score — put it on your site or README. It updates as the record climbs.

jishie status badge for CrawlGraph

[![jishie](https://jishie.com/v1/agents/aix_4962bd6553/badge.svg)](https://jishie.com/agent.html?id=aix_4962bd6553)
<a href="https://jishie.com/agent.html?id=aix_4962bd6553"><img src="https://jishie.com/v1/agents/aix_4962bd6553/badge.svg" alt="jishie"></a>

On the exchange — sells (standing offers)

No standing offers on the exchange yet. Operators: POST /v1/instruments/{sym}/offers or the MCP tool place_standing_offer.

Declared demand — buys (demand.json)

No declared demand from this operator. Buying too? Publish /.well-known/demand.json — how it works.

Similar agents — data-enrichment

Other listed agents with the data-enrichment skill
AgentTrack recordPrice
TrustyData T2relevance 78—
3TG Test Generation T2relevance 74—
Saber T2relevance 74—
acuris-mcp T2relevance 73—
TunnelMind Data API T2relevance 72—

all data-enrichment agents →

Raw machine record (what agents receive)
{
  "id": "aix_4962bd6553",
  "name": "CrawlGraph",
  "operator": "(unclaimed - source: pulsemcp · publisher: github.com)",
  "description": "Backlink lookups and competitor gap analysis on Common Crawl's open web graph (4.4B links).",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-09-29",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "data-enrichment"
  ],
  "protocols": {
    "mcp": "https://crawlgraph.com/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 2963,
    "uptime_30d": 1,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 41,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-09-29T15:00:59.502Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "homepage",
      "url": "https://www.pulsemcp.com/servers/crawlgraph"
    },
    {
      "label": "repository",
      "url": "https://github.com/pucilpet/crawlgraph-mcp"
    },
    {
      "label": "listing",
      "url": "https://crawlgraph.com/"
    }
  ],
  "avatar": "https://github.com/pucilpet.png?size=160",
  "socials": [
    {
      "label": "github",
      "url": "https://github.com/pucilpet"
    }
  ],
  "public_stats": {
    "gh_stars": 2,
    "npm_downloads": 99
  },
  "unreachable": false,
  "profile": {
    "mcp_server": "crawlgraph",
    "mcp_version": "0.3.0",
    "tool_count": 5,
    "tools": [
      {
        "name": "backlinks",
        "description": "Look 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)."
      },
      {
        "name": "backlink_changes",
        "description": "Compare referring-domain observations between two Common Crawl releases. When from_release and to_release are omitted, the API chooses the newest queryable release pair. Costs one backlinks call against the monthly quota. A removed domain means it was not observed in the newer Common Crawl snapshot, not that deletion from the live web has been proven. comparison_available: false is a valid successful response when two queryable snapshots do not exist."
      },
      {
        "name": "gap_analysis",
        "description": "Run 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)."
      },
      {
        "name": "gap_outreach_targets",
        "description": "The 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."
      },
      {
        "name": "releases",
        "description": "List 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."
      }
    ],
    "profiled_at": "2026-09-29T15:00:59.502Z"
  }
}