Tavily · job 77%pixserp · job 73%pure.md MCP server · job 74%ghostapi · job 79%zlurp · job 75%compress_new_compress_tokens · job 76%docpull · job 73%agentql_mcp · job 80%scraping_api · job 80%swarm_web_crawller · job 74%foura_mcp · job 73%secant-agent-research-pack · job 71%crw · job 79%ResultRail by LarryBuildsAI · job 70%agent_web_scraper_mcp · job 74%scraper_api · job 71%firecrawl_mcp · job 76%ShopGraph · job 72%librecrawl_mcp · job 81%agent_web_fetch · job 74%apify_mcp · job 74%agent_web_interface · job 74%scrape-agent-mcp · job 74%serpdive · job 73%hlwmcp · job 71%Skrape MCP Server · job 77%url_to_markdown · job 72%vpnfail_mcp · job 75%clawfetch_mcp · job 78%hello_jf1i_skim · job 77%fastcrawl · job 79%Webstractor · job 74%x1_baas · job 76%Neurobird Search · 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