MCP.Market

Agentreader MCP server

by ajanani1·io.github.ajanani1/agentreader-mcp·v1.0.0

11 pay-per-call web tools for AI agents, auto-paid in USDC on Base via x402. No API keys.

B78/100grade B
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

0 stars25 downloads/wk

Reviews

Write one

Nobody has reviewed Agentreader yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agentreader tools (11)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • clean_html

    Convert raw HTML you already have into clean markdown. Costs $0.003 USDC.

  • dns_lookup

    DNS lookup (A, AAAA, CNAME, MX, NS, TXT, SOA, SRV, CAA, PTR) with TTLs. Costs $0.001 USDC.

  • extract_links

    Extract all hyperlinks from a page with anchor text and internal/external classification. Costs $0.002 USDC.

  • extract_structured

    AI structured extraction: turn a web page or text into JSON matching YOUR JSON Schema (root type object). Guaranteed schema conformance. Costs $0.03 USDC.

  • page_metadata

    Get structured page metadata: title, description, canonical URL, OpenGraph, Twitter cards, favicons, JSON-LD types, headings. Costs $0.002 USDC.

  • parse_feed

    Parse an RSS/Atom/RDF feed into normalized JSON items (title, link, date, author, summary). Costs $0.003 USDC.

  • parse_sitemap

    Parse an XML sitemap or sitemap index into a URL list with lastmod/priority. Costs $0.003 USDC.

  • pdf_text

    Extract the full text of a PDF from a URL (up to 25 MB). Costs $0.01 USDC.

  • read_page

    Extract the main article from a web page as clean LLM-ready markdown (title, byline, publish date, markdown body). Costs $0.005 USDC via x402.

  • screenshot

    Render a page in a real headless browser and return a PNG screenshot. Costs $0.02 USDC.

  • summarize

    AI summarization of a web page URL or raw text. Dense, factual, preserves key numbers and names. Costs $0.02 USDC.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan2 source files scanned25/25
  • –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 45 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agentreader compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 57% of 48,255 servers
Tools
11
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
25
more than 11% of 12,191 servers with a package

What its tools let an agent do: 11 read

Install Agentreader in Claude Code, Cursor or VS Code

Runs npx -y agentreader-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agentreader-mcp -- npx -y agentreader-mcp
Add to Cursor

What the publisher says

From the Agentreader repository's README, as published. We do not edit it. Read it on GitHub

agentreader-mcp

MCP server for AgentReader — 13 pay-per-call tools for AI agents (web intelligence, OFAC sanctions screening, x402 trust data), paid automatically in USDC on Base via the x402 protocol. No API keys, no accounts: your agent's wallet pays $0.001–$0.05 per call and failed requests are never charged.

Tools

Setup

You need a wallet holding a little USDC on Base mainnet ($1 covers hundreds of calls). Use a dedicated agent wallet, not your main one.

Claude Desktop / Claude Code / any MCP client:

{
  "mcpServers": {
    "agentreader": {
      "command": "npx",
      "args": ["-y", "agentreader-mcp"],
      "env": { "AGENTREADER_PRIVATE_KEY": "0xYourAgentWalletPrivateKey" }
    }
  }
}

Also listed in the official MCP Registry as io.github.ajanani1/agentreader-mcp and on npm.

Environment variables:

  • AGENTREADERPRIVATEKEY (required) — private key of the paying wallet (USDC on Base; gas not needed, x402 uses gasless USDC authorizations)
  • AGENTREADER_API (optional) — API base URL, default https://agentreader.dev

How payment works

Each tool call hits the AgentReader API, receives an HTTP 402 with x402 payment requirements, signs a USDC authorization with your key, and retries. Settlement happens through the Coinbase CDP facilitator on Base mainnet. Errors (4xx/5xx) never settle — you only pay for delivered results.

API without MCP

The same endpoints are callable directly over HTTP with any x402 client: catalog · OpenAPI · llms.txt · x402 discovery

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Agentreader: common questions

Is Agentreader MCP server safe?
Mostly: it is graded B (78/100). Read the Agentreader safety report
How do I install Agentreader?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agentreader need an API key?
Yes. The registry entry asks for AGENTREADER_PRIVATE_KEY.
Is Agentreader maintained?
The last commit was 86 days ago (2026-08-10). The latest release is v1.0.0.
How does Agentreader compare with other MCP servers?
safety score 78/100 (higher than 57% of 48,255 servers); tools 11 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.