mcp · handle opencode_connect
Unlimited Agent · job 73%Flyto2 Runtime · job 78%Codex Bridge · job 74%docker_mcp_chatgpt · job 72%GPT Web Codex · job 75%codex_free · job 77%Agent MCP · job 81%VerityMCP · job 80%Chat2Local · job 73%Mika MCP · job 79%ChatGPT Remote Commander · job 77%MCP ChatGPT · job 75%Hermes MCP Bridge · job 71%ChatGPT MCP for Self-Hosted GitLab + ActualCoder · job 77%mcp_opencode · job 77%localMCP-chat · job 76%ChatGPT x Antigravity Bridge · job 78%Mac Developer Bridge · job 73%chat2shell · job 77%ChatGPT Windows MCP · job 77%shellway · job 75%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