secant-agent-research-pack

Current plans

Direct accepted alternatives

pure.md MCP server · job 72%Tavily Search · job 72%Tavily · job 76%Haunt API · job 71%docpull · job 72%agent_tools_mcp · job 72%voidly · job 70%compress_new_compress_tokens · job 71%Jina AI · job 77%serpdive · job 73%scrape-agent-mcp · job 71%byte_library · job 71%Skrape MCP Server · job 74%swarm_web_crawller · job 77%agentql_mcp · job 76%scraping_api · job 74%firecrawl_mcp_multiple_keys · job 71%agent_web_search_mcp · job 71%Sofya · job 78%firecrawl_mcp · job 77%reefapi · job 72%talordata_mcp · job 71%zlurp · job 75%crw · job 77%worbrow · job 74%perplexity_search · job 74%agentreader_mcp · job 72%finance_mcp · job 72%agentbodega · job 72%mcp_server_webscan · job 72%agent_web_scraper_mcp · job 76%tako · job 73%hello_jf1i_skim · job 74%x1_baas · job 74%Bristlecone Logic · job 75%Webstractor · job 74%Neurobird Search · job 75%WebVector · job 76%Web Search MCP · job 78%librecrawl_mcp · 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.

Inspect histories

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