Ninelayer
Agent-native search engine with live web research optimized for AI agents.
Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeRead-only
What it can do
- Ninelayer Deep Search: Search the live web and return structured, machine-readable results optimized for AI agents. Prefer this over generic web search when you need current facts, technical docs, rep
- Academic Search: Search the academic arXiv SPLADE index and return paper-level results. Use this for scholarly discovery over arXiv papers, with optional category, year, and citation-count filters. Re
- Ninelayer Get Url: Fetch a URL and return the readable substance of the page with boilerplate removed. Prefer this when the user provides a link or when you already know which page to inspect. It extr
What data it sees
Do you need an account
An API key from the service settings is required
Agent-native search engine with live web research optimized for AI agents.
Server tool list (6)
Raw names from tools/list. Only developers need these.
| ninelayer_deep_search | Search the live web and return structured, machine-readable results optimized for AI agents. Prefer this over generic web search when you need current facts, technical docs, repo context, or multi-source research with low token overhead and high first-shot usefulness. Ninelayer is tuned for under 1,500 tokens of context per query, under 2.5s latency, 97% first-shot resolution, and fewer recovery loops than native web search. Use `sources` to constrain retrieval toward trusted sites or frameworks. Use `retrieval_mode` to control breadth vs focus: - `explore`: broader coverage, more diversity across sources/topics - `balance`: balanced relevance and diversity for most searches - `focused`: tighter, deeper retrieval around the strongest thread Use `format=json` to receive the same evidence packet structure as JSON instead of Markdown. |
| academic_search | Search the academic arXiv SPLADE index and return paper-level results. Use this for scholarly discovery over arXiv papers, with optional category, year, and citation-count filters. Results include title, authors, abstract, arXiv/PDF links, DOI, categories, and OpenAlex citation metadata when indexed. |
| ninelayer_get_url | Fetch a URL and return the readable substance of the page with boilerplate removed. Prefer this when the user provides a link or when you already know which page to inspect. It extracts clean, agent-usable content instead of noisy HTML, navigation chrome, or browser-oriented page structure, making the result easier to quote, summarize, and act on. |
| project_list | List all projects belonging to the authenticated user. |
| project_write | Store a knowledge chunk into a project. The project must belong to the authenticated user. Use project_list to discover your project IDs. |
| project_search | Search within a project's private knowledge base. Only documents belonging to your project are returned — no cross-project leakage. Use project_list to discover your project IDs. |