extract_decisions

3 registry entries were observed exposing a tool named extract_decisions — 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 12,342 of 40,590 scannable entries (30%) — 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. @shinobiapps/shinobiMCPcommunitytrust 60/100 · B
    v0.3.1
    ↓ 469/wk

    Task spine + dead-end search + approvals for AI coding agents (Claude Code, Cursor, Cline, Continue.dev, Zed). Past dead ends are semantically searched before your agent writes code. Self-host or hosted — one brain across every device.

    ClaudeCursorCopilotGemini
    Tomislav KrizanMIT4mo agonpmGitHubobserved · static extraction
    mcpmodel-context-protocolclaude-codecursorai-coding-agentstask-management
  2. @clauderecallhq/cliMCPcommunitytrust 60/100 · B
    v0.183.2
    ↓ 114/wk

    Never lose a Claude Code or Codex session again. Local, fast, searchable memory over every session you've ever run.

    ClaudeCursorCopilotGemini
    Claude Recall HQSEE LICENSE IN LICENSE21d agonpmobserved · static extraction
    claudeclaude-codeanthropiccodexcodex-cliopenai
  3. @samuraizer/mcp-serverMCPcommunitytrust 60/100 · B
    v0.1.7

    Local MCP server for meeting transcripts, summaries, action items & decisions — no cloud.

    ClaudeCursorCopilotGemini
    io.github.UladzKhaUnknown1mo agonpmGitHubobserved · static extraction
    mcp

All indexed toolsSearch the registry for extract_decisions