memory_read

5 registry entries were observed exposing a tool named memory_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. affaan-m/ECCverified
   trust 85/100 · ACollectionobserved 2026-08-28 · static extraction
   The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code
2. io.github.amenophis1er/elefanteverified
   trust 85/100 · AMCP serverobserved 2026-06-13 · static extraction
   Open, Git-native memory protocol for MCP agents. Portable, versioned, human-editable.
3. @mnemoverse/mcp-memory-server
   trust 60/100 · BMCP serverobserved 2026-06-26 · static extraction
   Hosted memory for AI agents that learns from outcomes — one key across Claude, Cursor & ChatGPT.
4. io.github.mifactory-bot/mifactory-agent-memory
   trust 60/100 · BMCP serverobserved 2026-06-14 · static extraction
   Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
5. neurakeep
   trust 60/100 · BMCP serverobserved 2026-08-18 · static extraction
   Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools.

All indexed toolsSearch the registry for memory_read