mcp · handle agentgraph_server
gnosis_mcp · job 80%braintube_mcp · job 80%help_scout_mcp_server · job 80%neurostack · job 74%Quelvio · job 73%opencode_history_mcp · job 77%zoekt_mcp · job 74%liminary · job 76%Sovereign AI Blog · job 74%graphmind · job 74%core · job 78%rival_search_mcp · job 73%ai_search · job 75%knowledge_base_mcp_server · job 75%coworker_mcp · job 75%ACE Co-pilot · job 72%burn_mcp_server · job 75%PocketVault · job 78%Knowledge Base Plugin · job 74%Reed · job 78%LiteContext CLI · job 76%anysearch · job 74%navanithbharadwaj_stream · job 73%elasticsearch_mcp · job 73%context_awesome · job 79%Spark · job 79%mitosis · job 74%Okto Neuron · job 80%Pulipuli Blog Knowledge MCP · job 77%Coletivo · job 77%Infobroker · job 77%Agent-Reach MCP/A2A/Plugin Server · job 76%Slack MCP Server · job 76%CKG-NVIDIA-AI · job 76%Engram + Karpathy LLM Wiki · job 82%Caos Cerebro · job 77%rss_keyword_monitor · 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