mcp · handle threadboard
Cheap Labor · job 77%DeepBridge · job 72%Codex Bridge · job 71%Codex Local Ops · job 76%Qoder as Subagent · job 76%Hermes MCP Bridge · job 71%DSH × Codex Bridge · job 72%Board · job 70%Codex Subagent for Claude · job 77%Agent Review MCP · job 75%Chat MCP · job 76%Hermes ChatGPT Extension · job 75%mcp_opencode · job 79%ClaudeBase · job 76%Codex MD3 Expressive · job 77%Codex MCP DSH · job 73%Codex Progress Panel · job 76%Codex App MCP · job 75%Personal Agent · job 74%ChatGPT Local Connector · job 76%research-bridge · job 70%Codex Oracle Kit · job 81%Silva's Tab · job 76%ChatGPT Codex Handoff · job 74%Codex Thread Bridge · job 77%CoS Codex Bridge · job 79%Codex History MCP Bridge · job 74%codex_mcp_bridge · job 73%codex_control_plane_mcp · job 72%Agent Wire · job 75%Wingman · job 77%Codex CLI Sync MCP · job 70%index_codex_mcp · job 76%Jev Context MCP · job 78%Codex GitLab MCP Server · job 76%Cursodex · job 70%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series