mcp · handle agent_mcp_2
ChatGPT MCP for Self-Hosted GitLab + ActualCoder · job 75%ForgeBridge · job 72%OpenCode Connect · job 81%VerityMCP · job 82%macOS Local MCP · job 77%MCP DeskManager · job 76%mcp_claude_code · job 77%ohmyho.st MCP Server · job 75%RootRelay · job 79%ChatGPT Remote Commander · job 79%Continuity Orchestrator · job 72%DiscordMCP · job 80%MCP RemoteDev · job 77%Computer MCP · job 74%desktop_commander_mcp · job 78%MCP-MyPC · job 80%Project Moon · job 73%MCP ChatGPT · job 79%Mika MCP · job 79%shellway · job 84%docker_mcp_chatgpt · job 78%Mac Developer Bridge · job 74%Claude Codex MCP · job 78%codex_free · job 79%AgentDock MCP Harness · job 84%bcd · job 73%Warp Command Runner · job 74%Flyto2 Runtime · job 77%dot-mcp · job 74%Unlimited Agent · job 72%ChatGPT x Antigravity Bridge · job 77%Moonlight MCP Plugin · job 74%SentinelX · job 84%WebJjonku · job 80%wcgw · job 79%Codex Bridge · job 76%aimcp · job 73%godot-mcp · job 76%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