mcp · handle cheap_labor
mcp_opencode · job 80%index_codex_mcp · job 71%RootRelay · job 81%codex_free · job 79%claude_bridge_mcp · job 80%ChatGPT Web MCP · job 74%Chat MCP · job 85%Threadboard · job 77%Agent Review MCP · job 76%Codex Local Bridge · job 84%Codex GitLab MCP Server · job 76%Codex Oracle Kit · job 85%ChatGPT x Antigravity Bridge · job 75%Codex Git Commit Panel · job 71%GPT Web Codex · job 77%Ego Chat · job 83%Mika MCP · job 77%Codex CLI Sync MCP · job 71%Hermes MCP Bridge · job 72%ChatGPT Codex Handoff · job 80%ChatGPT Codex CLI Bridge · job 80%Antigravity MCP Bridge · job 74%SynAgent MCP · job 74%ChatGPT Local Connector · job 88%ChatGPT Wrapper · job 77%research-bridge · job 72%Codex Bridge · job 78%Codex Supervisor MCP · job 76%Codex ChatGPT Web MCP · job 82%Codex SSH Task Bridge · job 75%Qoder as Subagent · job 72%Codex Image MCP · job 71%CodexMCPBroker · job 71%ChatGPT MCP for Self-Hosted GitLab + ActualCoder · job 81%Codex Subagent for Claude · job 75%GitVerse Connector · job 73%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