NullClear Pre-Execution Firewall & Arbiter
io.github.Nullclear-Protocol/nullclear · v1.6.0 · 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
7-chain EVM/Solana 1-call Pre-Sign Firewall, Guarded RPC, Proxy/ABI Inspector & x402 Escrow
Source: https://github.com/Nullclear-Protocol/nullclear
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 14 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (nullclear_execute_escrow). Require confirmation before the agent calls them. |
What was checked
- https://api.nullclear.dev/mcp: answers without auth
- npm: @nullclear/mcp@1.6.0 (static checks only; code not executed)
Public tools: nullclear_scan_token, nullclear_inspect_contract, nullclear_decode_calldata, nullclear_simulate_transaction, nullclear_read_markdown, nullclear_preflight_guard, nullclear_discover_apis, nullclear_audit_paid_token, nullclear_score_wallet, nullclear_fetch_spot_price, nullclear_fetch_guarded, nullclear_execute_escrow, nullclear_check_reputation, nullclear_verify_mandate
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-nullclear-protocol-nullclear-a72467f5)