@agentutility/mcp-agentops

Trace, eval, and permission checks for autonomous work. · 4 tools · $0.008 – $0.02

INSTALL — CLAUDE DESKTOP

{
  "mcpServers": {
    "agentutility-agentops": {
      "command": "npx",
      "args": [
        "-y",
        "@agentutility/mcp-agentops"
      ],
      "env": {
        "X402_PRIVATE_KEY": "0xYOUR_PRIVATE_KEY_HEX"
      }
    }
  }
}

Path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).

INSTALL — CURSOR

{
  "mcpServers": {
    "agentutility-agentops": {
      "command": "npx",
      "args": [
        "-y",
        "@agentutility/mcp-agentops"
      ],
      "env": {
        "X402_PRIVATE_KEY": "0x..."
      }
    }
  }
}

Path: .cursor/mcp.json in your project root.

FUNDING

Send any amount of USDC on Base mainnet to the address derived from your X402_PRIVATE_KEY. The MCP server uses it to pay per call.

USDC on Base contract: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913

TOOLS (4)

tool	price	description
`agent-trace-brief`	$0.02	Turns a raw agent execution trace into a readable agent trace summary: an ordered step-by-step account of what the agent did, where it br…
`eval-case-generate`	$0.02	Eval case generator for an agent or LLM task: describe the task and get back a draft llm eval dataset of {input, expected, rubric} cases…
`mcp-tool-risk-score`	$0.02	Heuristic MCP tool risk review for an MCP tool manifest before you wire it into an agent.
`tool-call-diff`	$0.008	Deterministic tool call diff between two agent run sequences.