mcp · handle local_context
survivemem · job 79%claude-remote · job 75%mcp-code · job 79%Database-MCP · job 74%hey Bro! · job 73%mcp_database_server · job 81%Sherpa MCP · job 74%mcp-win-stdio · job 81%shellway · job 76%1C Claude Connector · job 74%mcp-sqlite-explorer · job 74%Claudemon · job 79%agent-hub · job 77%Phosphor · job 78%opencode-sandbox · job 73%Claude Executor · job 75%Knowledgebase MCP · job 74%MCP DeskManager · job 73%claude-inbox · job 74%stash · job 77%Board · job 73%cc-handoff · job 78%shortcuts_mcp · job 73%Aster Universal MCP · job 76%Deixion · job 79%claude_code_session_mcp · job 77%Polyagent · job 74%sous · job 76%Tuesday · job 76%PC File Bridge · job 75%freebase.cloud · job 73%Samsung Notes for Claude · job 74%MCP RemoteDev · job 82%SentinelX · job 74%Claude Voice Bridge · job 78%Trading212 MCP · job 75%homelab_mcp · job 75%srcbridge · job 74%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