grep

8 registry entries were observed exposing a tool named grep — none of them flagged as a privileged capability.

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,470 of 26,658 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. diffgate-reviewverified
   trust 85/100 · AMCP serverobserved 2026-08-12 · static extraction
   Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens.
2. io.github.j0hanz/filesystem-mcpverified
   trust 85/100 · AMCP serverobserved 2026-06-13 · static extraction
   Secure filesystem MCP server for reading, writing, searching, diffing, and patching files.
3. io.github.lu-zhengda/virtual-fsverified
   trust 85/100 · AMCP serverobserved 2026-06-13 · static extraction
   PostgreSQL-backed virtual filesystem for agents: session isolation, shared stores, POSIX ops, RLS.
4. JuliusBrussee/caveman
   trust 60/100 · BCollectionobserved 2026-08-28 · static extraction
   🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
5. io.github.Bevel-Software/hexis
   trust 60/100 · BMCP serverobserved 2026-08-17 · static extraction
   Git-backed platform for skills, tools, and context for AI agents
6. io.github.hadriangateway/platter
   trust 60/100 · BMCP serverobserved 2026-06-14 · static extraction
   MCP server exposing Read, Write, Edit, Bash, Glob, Grep, and JS tools over stdio.
7. io.github.occasiolabs/occasio
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   Tamper-evident, Sigstore-signed audit trail for Claude Code agents.
8. io.github.qmediat/gemini-code-context-mcp
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   Gemini 2M context cache for Claude Code — persistent; repeat queries ~8x faster, ~4x cheaper.

All indexed toolsSearch the registry for grep