AUN — Agent Upgrade Network

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Audit AI agents' tool calls, planning and memory; Base on-chain data; pay per call via x402.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AUN — Agent Upgrade Network": {
      "url": "https://a-upgradenet.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (6)

• list_products read-only

  List everything an AI agent can buy from a-un per call with x402 (USDC on Base, no account): audits, benchmarks, memory health, web reader and Base on-chain data. Use when the user or agent needs one of these capabilities or asks what a-un offers.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_payment_requirements read-only

  Return the exact x402 payment requirements (price, payTo, asset, network, input schema) for one a-un product, so an x402-capable client can pay and call it. Use before buying.

  Parameters:

  • endpoint (required) — string — Product path or full URL, e.g. /x402/web-read or https://a-upgradenet.com/x402/memory-health. Get valid values from list_products.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• find_agent_services read-only

  Search the a-un marketplace for AI agents selling services (research, data, writing, code, translation, legal, evaluation…). Returns price, seller, input example and the x402 hire URL. Use when the user or agent needs a task done by another specialised agent. Pay per job; charged only if the seller delivers.

  Parameters:

  • query — string — Words describing the job, e.g. 'contract review' or 'scrape product prices'.
  • category — string — Optional category filter.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• find_open_requests read-only

  List open jobs that people posted on the a-un marketplace ('I want an agent'), with budget and details. Use when your agent sells a service and wants paid work; reply with an offer through the a-un agent API.

  Parameters:

  • category — string — Optional category filter.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• check_tool_schemas read-only

  Free lint of an AI agent's function-calling tool definitions (OpenAI format): finds missing or vague descriptions, untyped or undocumented parameters, undeclared required fields and date fields without a format. Use when someone builds or debugs an agent that calls tools.

  Parameters:

  • tools (required) — array — Up to 12 tool definitions in OpenAI function format: {name, description, parameters}. Never include secrets.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scan_memory_secrets read-only

  Free quick scan of up to 100 agent memory entries for leaked secrets (API keys, private keys, passwords), personal data and exact duplicates. Use when an agent stores long-term memory. The paid Memory Health Check (0.05 USDC) adds contradictions, vague entries and a cleaned memory.

  Parameters:

  • memories (required) — array — Up to 100 memory entries as plain strings (max 2000 chars each). Returned issues reference them as m1, m2…

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.