Sofya · job 81%Veroq · job 78%Parallel Web Search · job 85%ninelayer · job 83%perplexity_search · job 75%taste_mcp · job 76%sparkforge · job 81%agentwings_exa_mcp_server · job 79%ezel · job 77%Swiss Truth MCP · job 77%crawlforge-mcp · job 81%neimo · job 76%agentready · job 81%rival_search_mcp · job 80%docimprint · job 78%web_researcher_mcp · job 80%tavily_mcp · job 75%anakin_agent_skills · job 78%horizon · job 76%wigolo_2026 · job 82%jina_mcp_server · job 81%tru8 · job 80%witnessd_mcp · job 78%fidenta_verify · job 76%clawfetch_mcp · job 77%anylens · job 77%ddg_search · job 79%anishdasmail_groundtruth · job 75%Knitify Health Research API · job 75%surfaceable_mcp_seo · job 81%Mnemom · job 75%mcp_server_webcrawl · job 80%wigolo · job 77%webhound_mcp · job 83%aidemos_mcp · job 81%seo_screaming_toad · job 77%bgpt_mcp · job 76%anakin · job 78%citeme · job 78%mcp_x402 · job 86%WebVector · job 80%OokCite MCP Server · job 77%HexWitness · job 77%tools · 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