read_skill

5 registry entries were observed exposing a tool named read_skill — 4 of them as a privileged capability (a name matching exec / write / delete keywords).

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,635 of 26,808 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.

1. dvalincodeverified
   trust 85/100 · AMCP serverobserved 2026-08-17 · static extraction
   Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.
2. io.github.perforce/p4plan-mcpprivilegedverified
   trust 85/100 · AMCP serverobserved 2026-06-13 · static extraction
   MCP server for P4 Plan — tasks, sprints, bugs, comments, custom fields via GraphQL API.
3. com.ottotheagent/otto-travelprivileged
   trust 60/100 · BMCP serverobserved 2026-08-10 · static extraction
   Plan, book, and manage business travel.
4. io.github.back1ply/agent-skill-loaderprivileged
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   Dynamically load Claude Code skills into AI agents without copying files.
5. io.github.xingbofeng/skill-deckprivileged
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   Expose local Agent Skills as adapter tools, MCP resources, MCP tools, and share artifacts.

All indexed toolsSearch the registry for read_skill