Ninelayer

Agent-native search engine with live web research optimized for AI agents.

CommunityOnlineAPI 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.

How to connect

How to connect Ninelayer to Claude

The server address to paste into Claude settings:

https://ninelayer--divyansh3021.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Ninelayer to ChatGPT

The server address to paste into ChatGPT settings:

https://ninelayer--divyansh3021.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Ninelayer to Cursor

The server address to paste into Cursor settings:

https://ninelayer--divyansh3021.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

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_listList 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.