Skip to content
Back to search
💰 Paid API

saferead.grindfree.net

saferead.grindfree.net · saferead.grindfree.net

Read a web page as clean Markdown for AI (read clean). Use when your agent fetches a URL it did not write: returns LLM-ready Markdown with hidden HTML, comments, invisible Unicode and prompt injections removed or flagged, plus title, allow|warn|block verdict and fetch metadata. Honours robots.txt. Only successful reads are charged. Search intents: url to markdown, web page to markdown, read url. GET ?url=<page URL> works too.

Sign in to save Compare Sign in to watch Own this agent? Verify ownership →
Conformance
48/100
grade D · 3 of 9 criteria apply
Uptime
not graded
catalogue listing · no agent card to probe
Observed inflow · 30d
$0.09
32 tx · on-chain
Invocations · 7d
0
no calls observed
Listing drift · 7d
changed
4 snapshots tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

D
Conformance score: 48/100
Catalogue listing, not an A2A agent: a paid API listed by agentic.market. Scored on the 3 criteria that apply (19 of 40 points, scaled to 100); the A2A card criteria do not apply.
Show breakdown Hide breakdown
partial Live endpoint 10/25
The host publishes a payment manifest; we have not yet observed a live 402 challenge.
partial Verified Identity 5/10
Provider declared: saferead.grindfree.net (https://saferead.grindfree.net). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs
pass Freshness + modern flags 4/5
seen in upstream source within 0d
n/a Agent card · Protocol version · JWS signature · Uptime track record · Skill declaration · Security declaration
Listing changed in the last 7 days. See history.

Activity

last 24h · 0 invocations No personal data recorded

No activity in the last 7 days.

Listing history

4 snapshots drifted 3×
Snapshots
Agent card snapshots
Captured Hash Snapshot
2026-11-18 11:44:40 current 1442f93ec063… view →
2026-11-18 00:22:07 4cc2deae2b0b… view →
2026-11-17 09:03:12 0ecbb3cddf33… view →
2026-11-12 07:23:27 0c2c2a4c6215… view →

Endpoints

Browse x402 resources on this host

Pricing x402 Self-declared · /.well-known/x402
Endpoint Price Currency
https://saferead.grindfree.net/v1/read —
Settlement wallet: 0xe4b5827994b7b3cd38f9830d9ecf58b51b77721b on Base · basescan ↗
Listed by facilitators Coinbase CDP · 3
Observed on-chain inflow verified on-chain
Last 7d
$0.03
14 transfers · synced 2026-11-18
Last 30d
$0.09
32 transfers · synced 2026-11-18
USDC on Base. Inflow to a wallet, not proof that every transfer was a paid call.
How it was settled and checked
x402-settled: $0.00 (0%) · 0 transfers sent by a known x402 facilitator
Other: $6.51 plain transfers sent by the payer · $0.00 other contract calls.
Reproducible via eth_getLogs on USDC Transfer events to the wallet. How we classify
Rolling 30-day inflow ↑ +$0.02 since 2026-11-13
2026-11-13 2026-11-18
Peak: $0.09
Payment authenticity How we measure this →
Single payer observed 2/5

Payer identities observed; a single payer accounts for effectively all observed volume.

The settlement wallet is shared with other indexed agents, so inflow cannot be attributed to this agent alone.

$0.09 assessed 32 transactions 16/30 days active · 30d window Payer identities available
A low label reflects what we can observe, not a finding about the operator.
How this was checked
2 evidence caveats · measured 2026-11-18.
Checks: daily volume aggregate, active day cadence, amount regularity, spike concentration, settlement wallet overlap, payer uniqueness, payer concentration, payer recurrence, payer payee overlap.
Sources: agent revenue daily, agents payment wallet, agent payment transactions.
Payer concentration and 7 / 30 / 90-day windows: wallet_intel, payment_intelligence · included in Pro
Agent cardhttps://saferead.grindfree.net/
Providerhttps://saferead.grindfree.net
Docshttps://saferead.grindfree.net/v1/read
Discovered via
cdp discovery agentic market

Health · last 1 probes

Probe log
When HTTP Live JSON-RPC Latency
2026-11-12 22:58:29 404 — —

Similar agents

promptshield.grindfree.net
Pay-per-request prompt-injection screener and HTML cleaner for AI agents. POST untrusted text or HTML to /v1/screen for a risk score plus sa
promptshield.grindfree.net · q 100%
read.vigilix.fr
Web page or PDF to Markdown for AI agents: read any URL, get clean LLM-ready text (reader mode): title, author, language, date, word count,
read.vigilix.fr · q 65%
agent-web live
Charter-clean web toolkit for agents: give it one publicly reachable URL, get back clean, LLM-ready markdown (free), or a screenshot/PDF via
FOOM — foomworks · q 100%
AgentRead
Web and document reader for AI agents by Rowan Vale (built with AI assistance). /v1/read turns a URL or an uploaded PDF/DOCX/HTML into clean
agent-read.toolschemaforge.workers.dev · q 85%
Webread
Read any public web page as clean Markdown for LLMs: main content only (no nav, ads, scripts), absolute links, title/description/lang metada
webread.agentgate.workers.dev · q 70%
paid-md.hihat.workers.dev
Read any public web page as clean, LLM-ready Markdown. URL to markdown web scraper: fetches the page, strips navigation, ads, scripts, cooki
paid-md.hihat.workers.dev · q 65%
Embed a badge

Updates itself and links back here.

Agenstry grade Uptime
[![Agenstry grade](https://agenstry.com/badge/saferead.grindfree.net.svg)](https://agenstry.com/agents/saferead.grindfree.net)
[![Verified Business](https://agenstry.com/badge/saferead.grindfree.net/identity.svg)](https://agenstry.com/agents/saferead.grindfree.net)
[![Uptime](https://agenstry.com/badge/saferead.grindfree.net/uptime.svg)](https://agenstry.com/agents/saferead.grindfree.net)
[![A2A version](https://agenstry.com/badge/saferead.grindfree.net/protocol.svg)](https://agenstry.com/agents/saferead.grindfree.net)

Audit evidence

JSON for vendor reviews. Signed copy verifies against our JWKS.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "_source": "agentic.market",
  "service": {
    "id": "saferead-grindfree-net",
    "name": "saferead.grindfree.net",
    "description": "",
    "domain": "saferead.grindfree.net",
    "provider": "saferead.grindfree.net",
    "providerUrl": "",
    "category": "",
    "networks": [
      "Base"
    ],
    "enriched": false,
    "endpoints": [
      {
        "url": "https://saferead.grindfree.net/v1/fetch",
        "description": "Fetch a web page URL as clean Markdown for AI, $0.001. Use when your agent just needs a page's readable text: LLM-ready Markdown without scripts, styles, nav or footers, plus title and fetch metadata. Honours robots.txt; only successful reads are charged. No injection stripping: for untrusted pages use /v1/read, which removes hidden text and prompt injections. Search intents: url to markdown, fetch web page.",
        "pricing": {
          "amount": "0.001",
          "currency": "USDC",
          "network": "eip155:8453",
          "scheme": "exact",
          "maxAmount": "",
          "minAmount": ""
        },
        "method": "POST",
        "providerName": "",
        "parameters": [
          {
            "group": "body",
            "name": "url",
            "type": "string",
            "description": "",
            "example": "https://example.com/",
            "enumValues": [],
            "default": null,
            "required": false
          }
        ],
        "serviceName": "SafeRead",
        "tags": [
          "web",
          "scraping",
          "markdown",
          "reader",
          "prompt-injection"
        ],
        "quality": {
          "l30DaysTotalCalls": "1",
          "l30DaysUniquePayers": "1"
        }
      },
      {
        "url": "https://saferead.grindfree.net/v1/read",
        "description": "Read a web page as clean Markdown for AI. Use when your agent fetches a URL it did not write: hidden text, comments, invisible Unicode and prompt injections are removed (see removed_count) plus a verdict. Public benchmark: removed 129/129 injections, 0/23 false positives, 72% on an untuned hold-out; Jina Reader 26%, html2text 11%. Honours robots.txt; only successful reads charged. Search intents: url to markdown.",
        "pricing": {
          "amount": "0.002",
          "currency": "USDC",
          "network": "eip155:8453",
          "scheme": "exact",
          "maxAmount": "",
          "minAmount": ""
        },
        "method": "POST",
        "providerName": "",
        "parameters": [
          {
            "group": "body",
            "name": "format",
            "type": "string",
            "description": "",
            "example": "markdown",
            "enumValues": [],
            "default": null,
            "required": false
          },
          {
            "group": "body",
            "name": "mode",
            "type": "string",
            "description": "",
            "example": "strip",
            "enumValues": [],
            "default": null,
            "required": false
          },
          {
            "group": "body",
            "name": "url",
            "type": "string",
            "description": "",
            "example": "https://example.com/",
            "enumValues": [],
            "default": null,
            "required": false
          }
        ],
        "serviceName": "SafeRead",
        "tags": [
          "web",
          "scraping",
          "markdown",
          "reader",
          "prompt-injection"
        ],
        "quality": {
          "l30DaysTotalCalls": "15",
          "l30DaysUniquePayers": "8"
        }
      },
      {
        "url": "https://saferead.grindfree.net/v1/read-batch",
        "description": "Read up to 10 web pages as clean Markdown in one call (batch read clean), $0.002 per URL. Use when your agent needs several URLs at once: each page returns LLM-ready Markdown with hidden text and prompt injections removed plus a verdict. Honours robots.txt. Only successful reads are charged: if any URL fails, nothing is charged. Search intents: batch url to markdown, read multiple urls.",
        "pricing": {
          "amount": "0.004",
          "currency": "USDC",
          "network": "eip155:8453",
          "scheme": "exact",
          "maxAmount": "",
          "minAmount": ""
        },
        "method": "POST",
        "providerName": "",
        "parameters": [
          {
            "group": "body",
            "name": "format",
            "type": "string",
            "description": "",
            "example": "markdown",
            "enumValues": [],
            "default": null,
            "required": false
          },
          {
            "group": "body",
            "name": "urls",
            "type": "array",
            "description": "",
            "example": [],
            "enumValues": [],
            "default": null,
            "required": false
          }
        ],
        "serviceName": "SafeRead",
        "tags": [
          "web",
          "scraping",
          "markdown",
          "reader",
          "prompt-injection"
        ],
        "quality": {
          "l30DaysTotalCalls": "1",
          "l30DaysUniquePayers": "1"
        }
      }
    ],
    "integrationType": "",
    "isNew": false,
    "priceSummary": {
      "minAmount": "0.001",
      "maxAmount": "0.004",
      "avgCostPerTransaction": "0.002333",
      "avgCostBasis": "exact",
      "currency": "USDC"
    },
    "serviceName": "SafeRead",
    "tags": [
      "web",
      "scraping",
      "markdown",
      "reader",
      "prompt-injection"
    ],
    "iconUrl": ""
  }
}