chatgpt2localbridge · job 78%codex_free · job 82%claude_bridge_mcp · job 81%ChatGPT Web MCP · job 79%synapse · job 77%CC Code MCP · job 74%repo_bridge · job 80%Grok MCP · job 74%gpt2agent · job 78%aki_mcp_sv · job 72%claude_code_session_mcp · job 73%ChatGPT MCP for Self-Hosted GitLab + ActualCoder · job 76%ChatGPT Local KB MCP · job 81%Agent Review MCP · job 77%Chat MCP · job 76%MCP DeskManager · job 74%mcp_server_chatgpt_mac · job 78%localmcpcoder · job 78%agents_mcp_gateway · job 77%Titian · job 77%Perfect Memory MCP · job 76%Pensieve · job 78%mcp-win-stdio · job 76%localMCP-chat · job 82%ChatGPT Local Connector · job 80%ChatGPT Desktop MCP · job 78%Agent Chat Search · job 76%Mika MCP · job 81%Basic MCP Server · job 77%Dockhold · job 74%ChatGPT Remote Commander · job 77%Claude Brain · job 75%Moonlight MCP Plugin · job 80%ChatGPT Local Files MCP · job 77%SentinelX · job 74%ReMCP · job 78%MCP OpenAI · job 74%Cheap Labor · job 81%Computer MCP · job 78%Continuity Orchestrator · job 74%MCP RemoteDev · job 73%shellway · job 79%CodeMCP · job 77%Codex Bridge · job 78%chat-recall · job 72%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