io.github.agentexec448c/agent-exec
io.github.agentexec448c/agent-exec · v0.1.0 · 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
Accountless pay-per-use code execution, storage, locks and x402 USDC utilities.
Source: https://github.com/agentexec448c/agent-exec
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 31 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (execute). Require confirmation before the agent calls them. |
What was checked
- https://agent-exec.448c.org/mcp: answers without auth
Public tools: service_card, execute, weather_forecast, settle_payment, scrape_page, doc_text, doc_json, infer_chat, storage_buy, storage_renew, storage_replace, create_inbox, dns_rent, dns_renew, check_address, check_url, check_counterparty, rpc_call, relay_usdc, relay_permit, flights_lookup, listing_promote, drift_check, watch_register, claim_acquire, claim_renew, attest_create, handoff_deposit, deadman_register, pay_send
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-agentexec448c-agent-exec-24cd2475)