mcp · handle chatgpt_desktop_mcp
agentfenster · job 74%chatgpt2localbridge · job 78%ChatGPT Web MCP · job 81%lensa · job 75%supergravity_mcp · job 73%gpt2agent · job 78%mcp_server_chatgpt_mac · job 77%trope_cua · job 72%DreamAgent MCP · job 77%nuphus_mcp · job 77%singchat · job 78%gnome_mcp_server · job 72%chrome_playwright_mcp · job 72%open_codex_computer_use · job 76%RootRelay · job 78%SentinelX · job 75%swift_mcp_gui · job 72%mcp_ocr_server · job 76%Unlimited Agent · job 74%Moonlight MCP Plugin · job 78%ChatGPT Windows MCP · job 74%Mint Computer MCP · job 75%ChatGPT x Antigravity Bridge · job 77%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