mcp · handle agentgraph_server
braintube_mcp · job 80%burn_mcp_server · job 75%help_scout_mcp_server · job 80%coworker_mcp · job 75%neurostack · job 74%liminary · job 76%knowledge_base_mcp_server · job 75%opencode_history_mcp · job 77%graphmind · job 74%core · job 78%anysearch · job 74%rival_search_mcp · job 73%navanithbharadwaj_stream · job 73%elasticsearch_mcp · job 73%ai_search · job 75%context_awesome · job 79%gnosis_mcp · job 80%PocketVault · job 78%Reed · job 78%Okto Neuron · job 80%NotedThat · job 75%Quelvio · job 73%zoekt_mcp · job 74%Sovereign AI Blog · job 74%ACE Co-pilot · job 72%LiteContext CLI · job 76%Spark · job 79%ESG Hub · job 77%mitosis · job 74%Infobroker · job 77%Knowledge Base Plugin · job 74%CKG-NVIDIA-AI · job 76%Slack MCP Server · job 76%rss_keyword_monitor · job 76%Coletivo · job 77%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