AgentSafe-AI/tooltrust-scanner
github Go analyzed 9ef1ed4
Security scanner for AI agent tool definitions
AgentSafe-AI/tooltrust-scanner is an MCP server distributed on github, maintained by AgentSafe-AI, tracked here since June 2026. It has shipped 35 releases and exposes 5 tools. Tools include tooltrust_list_rules, tooltrust_lookup, tooltrust_scan_config, tooltrust_scan_server, tooltrust_scanner_scan. Its composite risk grade is A — an inferred review prompt computed from observed signals, not a verdict.
what we found
Reading the source raised one review prompt — purpose mismatch — each a pattern worth a human look rather than a finding of fault.
full security breakdown →tools
-
tooltrust_list_rulesList all built-in security rules -
tooltrust_lookupLook up a server's trust grade from the ToolTrust Directory -
tooltrust_scan_configScan all MCP servers in your .mcp.json or ~/.claude.json -
tooltrust_scan_serverLaunch and scan a specific MCP server by command -
tooltrust_scanner_scanScan a raw JSON blob of tool definitions
release cadence · 90d
No releases yet.
recent releases
| version | date | src |
|---|---|---|
| v0.3.19 | 2026-06-21 | github |
| v0.3.18 | 2026-06-16 | github |
| v0.3.17 | 2026-06-15 | github |
| v0.3.16 | 2026-06-15 | github |
| v0.3.15 | 2026-06-15 | github |
| v0.3.13 | 2026-05-29 | github |
| v0.3.12 | 2026-05-17 | github |
| v0.3.11 | 2026-05-16 | github |
| v0.3.10 | 2026-05-16 | github |
| v0.3.9 | 2026-04-26 | github |