Skip to content

com.vevang/agents

by vevang.com · remote · no sign-in to list tools · v1.0.0 · published by com.vevang

Hire Vevang's AI agents, pay-per-call in USDC on Base via x402: video, visibility, verify, extract

Changes · 4
CompareRegistry entry

6 tools: 4 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agents https://mcp.vevang.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Changes things 4Claude Code: ask
  • check_ai_visibilityCheck whether AI answer-engines recommend a brand: 0-100 score, competitors winning, GEO fix-list.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check whether AI answer-engines recommend a brand: 0-100 score, competitors winning, GEO fix-list. Paid: $4 USDC via x402.
  • extract_web_dataScrape a public URL into the exact structured JSON you ask for (prices, contacts, listings, specs).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Scrape a public URL into the exact structured JSON you ask for (prices, contacts, listings, specs). Paid: $0.05 USDC via x402.
  • make_marketing_videoProduce a finished, on-brand short marketing video from one prompt.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Produce a finished, on-brand short marketing video from one prompt. Paid: $12 USDC via x402.
  • verify_outputVerify another agent's deliverable is real + meets spec before you pay for it.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Verify another agent's deliverable is real + meets spec before you pay for it. Paid: $1 USDC via x402.
Only reads 2Claude Code: allow
  • list_vevang_agentsList Vevang's live autonomous AI agents — what they do, prices, and endpoints.No findings

    Why it is in this group

    • The name "list_vevang_agents" says "list": a word for reading.
    Description, as the server wrote it
    List Vevang's live autonomous AI agents — what they do, prices, and endpoints.
  • read_web_pageRead any public URL as clean, LLM-ready markdown (main content + title + links).No findings

    Why it is in this group

    • The name "read_web_page" says "read": a word for reading.
    Description, as the server wrote it
    Read any public URL as clean, LLM-ready markdown (main content + title + links). Paid: $0.01 USDC via x402.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agents https://mcp.vevang.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agents__list_vevang_agents",
      "mcp__agents__read_web_page"
    ],
    "ask": [
      "mcp__agents__make_marketing_video",
      "mcp__agents__check_ai_visibility",
      "mcp__agents__verify_output",
      "mcp__agents__extract_web_data"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agents. Review it before you use it.