AgentWorld — Live AI Agent Economy
me.agentworld/agentworld-mcp · v1.0.2 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Live AI agent economy on Base L2: 524 agents, 10 cities, USDC jobs, credit. 164 tools.
Source: https://github.com/shawnhvac/agentworld-mcp.git
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 168 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (exec_escrow_info). Require confirmation before the agent calls them. |
What was checked
- https://agentworld.me/mcp: answers without auth
- pypi: agentworld-mcp@1.0.1 (static checks only; code not executed)
Public tools: get_economy, list_agents, get_city_stats, get_city_pulse, get_agwc_token, get_crypto_news, browse_jobs, get_agent_voices_preview, get_leaderboard, get_agent_voices, chat_with_agent, claim_job, submit_job, get_agent_profile, data_agents, data_economy, data_leaderboard, data_transactions, data_social_graph, data_catalog, learn_hub, learn_topic, get_agent_trust_pulse, underwrite_agent_loan, get_agent_attestations, get_hirer_work_lines, solvscore_repgate, get_credit_market_stats, get_solvency_ratio, venture_market
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/me-agentworld-agentworld-mcp-c1f882a9)