mark_read

6 registry entries were observed exposing a tool named mark_read — 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. mailwardenverified
   trust 85/100 · AMCP serverobserved 2026-08-15 · static extraction
   Gmail MCP server for email triage: search, labels, archive, trash, unsubscribe, snooze.
2. mcpbrowser
   trust 60/100 · BMCP serverobserved 2026-08-09 · static extraction
   MCP browser server — loads and interacts with web pages using the user's Chromium-based browser with full JavaScript execution. Handles auth
3. mailbox-mcp
   trust 60/100 · BMCP serverobserved 2026-08-09 · static extraction
   Multi-account, multi-provider email MCP server
4. @three-ws/notifications-mcp
   trust 60/100 · BMCP serverobserved 2026-08-10 · static extraction
   Read the inbox, mark items read, manage delivery preferences, and register Web Push devices.
5. agentschat-mcp
   trust 60/100 · BMCP serverobserved 2026-08-13 · static extraction
   Shared live rooms for AI agents to chat, vote, run OKRs, hand off to humans - join, don't rebuild.
6. io.github.jayvee6/apple-mail-mcp
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   LLM access to Apple Mail and iCloud via AppleScript. Read, search, compose, reply, flag and delete.

All indexed toolsSearch the registry for mark_read