Every tool here can tell you what a document says. InfraNodus tells you what it conspicuously does not — which topics sit unconnected, and what question would bridge them. For research, editorial planning or competitive analysis that is the more valuable output, and it comes from graph structure rather than from asking a model to speculate. Auto-transcribing a YouTube URL into the same pipeline is a practical touch.
InfraNodus' endpoint for their text-network analysis product. Thirty-two tools, and the distinctive ones are not about building graphs but about reading what is missing from them.
- generate_knowledge_graph and create_knowledge_graph — from text, a URL, or a YouTube video that gets auto-transcribed; the second saves it
- generate_content_gaps — areas of discourse that are underdeveloped, found by looking for topics that are not well linked
- generate_research_questions and generate_research_ideas — questions and directions that bridge those gaps
- generate_topical_clusters and generate_ontology_graph — clusters from a source, or an AI-generated reasoning ontology
- generate_responses_from_graph and generate_contextual_hint — answers synthesised from the graph's structure, and a structural summary for GraphRAG
- analyze_text and analyze_existing_graph_by_name — full analysis with clusters, concepts and gaps
OAuth 2.0 bearer, header only — and the consent step is unusual: you paste your InfraNodus API key on their auth page, so OAuth wraps an API-key handoff. Local deployments use an environment variable instead, with anonymous use allowed for 70 requests.
Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen