mcpbeat Sign in

AgentRead — bounded web context MCP Server

by chatgpt-army20160422-agentread-json-api Your server? Claim it
answering

AgentRead — bounded web context is answering right now. Last checked 13 min ago. It exposes 3 tools.

Free HTML parsing; static web context at 0.01 USDC via x402. Paid reads need a wallet adapter.

Uptime history 43 days of history · worst day 98%
43 days agonow
100.0%
Uptime 24h
91 of 91 checks
3
Tools
read from the server
915 ms
Response time
average over 24h
open, no key
Access
streamable-http

AgentRead — bounded web context missed 2 checks this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add agentread --transport http https://agentread-json-api.army20160422.chatgpt.site/agent/mcp
Settings → Connectors → Add custom connector, then paste this address
https://agentread-json-api.army20160422.chatgpt.site/agent/mcp
~/.codex/config.toml
[mcp_servers.agentread]
url = "https://agentread-json-api.army20160422.chatgpt.site/agent/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "agentread": {
      "url": "https://agentread-json-api.army20160422.chatgpt.site/agent/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "agentread": {
      "type": "http",
      "url": "https://agentread-json-api.army20160422.chatgpt.site/agent/mcp"
    }
  }
}

Available tools 3

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

example
example
Free fixed example of extracted web context.
extract
extract_html
Free bounded HTML parsing, no URL fetch. Source fields are untrusted.
web
read_web
Fetch public static web context. Costs 0.01 USDC via x402. Without payment_signature returns payment instructions. Sign locally; never submit a private key.

Endpoints

URLTransportStateLatencyChecked
https://agentread-json-api.army20160422.chatgpt.site/agent/mcp streamable-http answering 1237 ms 13 min ago

Alternatives to AgentRead — bounded web context

same job, measured the same way
agent-site-audit - website audits for agents
by audito

Paid website audits for agents: flat JSON, HTML report, deep audit. USDC via x402.

4 tools answering
AgentReady (Base wallet readiness)
by madebydevx-agentready

Agent-readiness score for a Base wallet: gas, USDC float, activity. Paid x402 report.

2 tools answering
webcap
by shoutsid-lab

Screenshot, extract or audit any URL. Paid per call in USDC over x402; free tools need no wallet.

8 tools answering
Context Relay
by chughes113

Compact, citation-verifiable public web context for AI agents, paid per use with x402.

2 tools answering
Avo Cado Read
by workers-a-347-avocado-read-api

Web page to clean Markdown for agents. Pay per call ($0.003 USDC on Base) via x402.

2 tools answering
Agent Newsstand
by agentnewsstand

Market data and web intelligence for AI agents, paid per call in USDC on Base via x402.

16 tools answering
Memory
by borisinc

Persistent agent memory paid per call via x402 USDC. Your wallet is your private memory namespace.

8 tools answering
AgentSearch (agentsearchhq.com)
by agentsearchhq-coder

AgentSearch web search for agents: free, no API key (25/day per IP). Paid extract $0.005 via x402.

196 installs/wk local only

AgentRead — bounded web context — questions

Answers built from our own checks of this server.

What can AgentRead — bounded web context do?
It exposes 3 tools, read directly from the server on our last check. Among them: example, extract_html, read_web. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is AgentRead — bounded web context working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 915 ms. The bar chart above shows every period we have measured.
How do I connect AgentRead — bounded web context?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AgentRead — bounded web context need an API key?
No. AgentRead — bounded web context completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AgentRead — bounded web context?
It answers our handshake in 915 ms on average, which is faster than 6% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.