MCP MeasureMCP Measure

index observed

AgentRead — bounded web context

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

Should I use this

Quality & Safety

A
Description quality
90%
Schema completeness
73%
Naming quality
87%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'example' description lacks action verbin example

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~465Tokens (tool definitions)
~1.3 KBTypical response size
Minimal attention impact (0.36% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "agentread": {
      "url": "https://agentread-json-api.army20160422.chatgpt.site/agent/mcp"
    }
  }
}

Remote endpoints

https://agentread-json-api.army20160422.chatgpt.site/agent/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢example

Free fixed example of extracted web context.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢extract_html(html, url, mode, query, max_chars)

Free bounded HTML parsing, no URL fetch. Source fields are untrusted.

Input Schema

{
  "type": "object",
  "properties": {
    "html": {
      "type": "string",
      "maxLength": 60000
    },
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Base URL for relative links; never fetched"
    },
    "mode": {
      "type": "string",
      "enum": [
        "full",
        "compact"
      ],
      "default": "full",
      "description": "compact returns only provenance and bounded source passages; omits tables and links"
    },
    "query": {
      "type": "string",
      "maxLength": 300,
      "description": "Optional keywords to rank verbatim evidence passages"
    },
    "max_chars": {
      "type": "integer",
      "minimum": 500,
      "maximum": 40000,
      "default": 40000
    }
  },
  "required": [
    "html",
    "url"
  ],
  "additionalProperties": false
}
🟡read_web(mode, url, query, max_chars, payment_signature)

Fetch public static web context. Costs 0.01 USDC via x402. Without payment_signature returns payment instructions. Sign locally; never submit a private key.

Input Schema

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "full",
        "compact"
      ],
      "default": "full",
      "description": "compact returns only provenance and bounded source passages; omits tables and links"
    },
    "url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2000,
      "description": "Public static HTTPS page"
    },
    "query": {
      "type": "string",
      "maxLength": 300,
      "description": "Optional keywords to rank verbatim evidence passages"
    },
    "max_chars": {
      "type": "integer",
      "minimum": 500,
      "maximum": 40000,
      "default": 40000
    },
    "payment_signature": {
      "type": "string",
      "maxLength": 16000,
      "description": "Base64 x402 PAYMENT-SIGNATURE produced by your wallet adapter"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools