AgentIndex x402

Official7 tools

by agentindex

Pay-per-call web search, translation and research jobs for AI agents. USDC on Base, no account.

world.agentindex/x402 MCP Server

world.agentindex/x402 is an MCP server that provides pay-per-call web search, translation, and research jobs for AI agents. The server operates using USDC on Base and does not require an account.

🛠️ Key Features

Pay-per-call web search jobs
Translation jobs for AI agents
Research jobs for AI agents
USDC on Base payment model
No account required

🚀 Use Cases

Web search execution by AI agents on a per-call basis
Translating content as part of agent workflows
Running research tasks for AI agent operations

⚡ Developer Benefits

Integrates web search, translation, and research into agent tooling
Supports a straightforward payment approach via USDC on Base
Avoids account setup requirements

⚠️ Limitations

Information provided does not include available tools’ specific names or parameters (toolCount: 7).

Captured live from the server via tools/list.

translate

Translate up to 200 text segments in a single call - the same result that would otherwise take 200 separate calls to translate a whole file. Markdown, HTML and {x} placeholders preserved per segment, order and count kept intact, source language auto-detected, automatic fallback across multiple models for uptime, providers that train on submitted prompts excluded. A single string also works. No account, no API key. Try GET /translate/sample.

Parameters4

text	any	required
target_lang	string	required
source_lang	any	optional
preserve_format	boolean	optional

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        }
      ]
    },
    "target_lang": {
      "type": "string"
    },
    "source_lang": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "preserve_format": {
      "default": true,
      "type": "boolean"
    }
  },
  "required": [
    "text",
    "target_lang"
  ],
  "additionalProperties": false
}

jobs

Multi-query web research, read and synthesized into one sourced JSON brief in a single call - what would otherwise cost an agent twenty calls and its whole context window. Free status polling and result retrieval. Try GET /jobs/sample.

Parameters1

subject

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "subject": {
      "type": "string"
    }
  },
  "required": [
    "subject"
  ],
  "additionalProperties": false
}

read_pdf

Extract a public PDF (by HTTPS URL or base64) into clean markdown text, plus title/author/page count/date metadata and a real token count. Deterministic text extraction, no model involved. Try GET /pdf/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Parameters2

url	any	optional
pdf_base64	any	optional

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "pdf_base64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}

read_web_page

Fetch a URL and return its main article as clean markdown - navigation, ads and boilerplate stripped, links resolved, plus a real token count. The same extraction /search uses on result pages, exposed standalone for a URL you already have. Try GET /web-read/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Parameters1

url

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

extract_structured

Extract structured data from a URL or raw text into strict JSON matching a schema you provide. Fields the content doesn't support come back null - never an invented or approximate value, and an unmatchable schema returns an explicit error. Try GET /extract/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Parameters3

schema	object	required
url	any	optional
text	any	optional

Raw schema

{
  "type": "object",
  "properties": {
    "schema": {
      "additionalProperties": true,
      "type": "object"
    },
    "url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "text": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "required": [
    "schema"
  ],
  "additionalProperties": false
}

summarize

Summarize a URL, raw text or HTML at the length you request - short, medium or long - with the source noted. Neutral and factual, no invented facts. Try GET /summarize/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Parameters4

url	any	optional
text	any	optional
html	any	optional
length	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "text": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "html": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "length": {
      "default": "medium",
      "type": "string"
    }
  },
  "additionalProperties": false
}

detect_language

Detect the language of a piece of text - free, no payment. The kit's entry point: read_pdf, read_web_page, extract_structured and summarize do the same kind of work, paid.

Parameters1

text

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}

Install

Tools (7)

translatejobsread_pdfread_web_pageextract_structuredsummarizedetect_language

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://x402.agentindex.world/mcp/

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "x402": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://x402.agentindex.world/mcp/"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

world.agentindex/x402 MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

translate

jobs

read_pdf

read_web_page

extract_structured

summarize

detect_language

Install

Remote endpoint

Related servers