Skip to content
New Site Radar logo

New Site Radar MCP server

Which servers in the official MCP registry are New Site Radar's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-24

← Back to New Site Radar

Whose server it is
  • Registry namecom.newsiteradar/new-site-radarverified in the MCP registry

The registry name sits under newsiteradar.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools7
  • Server calls itselfnew-site-radar
  • Server version1.0.1
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 109 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: scan monthly rankings of new AI tool sites by traffic growth; check traffic and revenue estimates for a specific new site; pull ranking data into AI agents via MCP.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "scan monthly rankings of new AI tool sites by traffic growth", the likely first call is top_rising.
  • For "check traffic and revenue estimates for a specific new site", the likely first call is get_site.
  • For "pull ranking data into AI agents via MCP", the likely first call is top_rising.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer175 ms
  • Space in an agent's context≈ 1,392 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · scan monthly rankings of new AI tool sites by traffic growth
  • can do · check traffic and revenue estimates for a specific new site
  • can do · pull ranking data into AI agents via MCP

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers7 tools · read 2026-10-24
  • search_sites

    Search the current monthly board of new AI tool sites by keyword (domain / name / description) and filters (category, site type, monthly-visits bucket, MoM bucket, payment detected). Returns board rows with visits, MoM, organic share, DR…

  • get_site

    Everything we have on one tracked site: monthly traffic history, channels, top countries, engagement, keywords, backlinks/DR, tech stack, payment providers with fingerprint evidence, pricing, estimated revenue range and grade, cross-check…

  • top_rising

    The top N of this month's rising-sites board (ordered by absolute monthly-visit growth), optionally within one category. Requires an API key (Authorization: Bearer nsr_… or x-api-key: nsr_…): free key from https://newsiteradar.com/mcp (20…

  • revenue_signals

    Top N sites on the revenue-signals board: payment provider detected (Stripe, Paddle, Lemon Squeezy …), main price, estimated monthly revenue range (USD) and grade A/B. Optional category and payment-provider filters. Requires an API key…

  • list_categories

    Category slugs on the current board (with site counts), plus the valid values for search_sites filters (type, visits, mom, payment). Requires an API key (Authorization: Bearer nsr_… or x-api-key: nsr_…): free key from…

  • model_releases

    Newest AI model releases from 26 labs (official announcements, blogs, open-weights repos), optionally by company and since a date. Requires an API key (Authorization: Bearer nsr_… or x-api-key: nsr_…): free key from…

  • get_methodology

    How the boards are built: data sources, listing thresholds, cross-check bands, confidence and revenue grades, update cadence. Requires an API key (Authorization: Bearer nsr_… or x-api-key: nsr_…): free key from…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "new-site-radar": {
      "type": "http",
      "url": "https://newsiteradar.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http newsiteradar https://newsiteradar.com/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://newsiteradar.com/api/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.