Skip to content

rowb MCP server

Which MCP servers are rowb's own, from the official registry and from asking its own domain, 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 rowb

Whose server it is
  • Registry nameapp.rowb.ai-visibility/auditverified in the MCP registry

The registry name sits under rowb.app. 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
  • Tools1
  • Server calls itselfai-visibility
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 335 ms.

Should an agent connect itNot proven either way yet
  • Its tools do check whether AI crawlers can read a website, but not record fishing catches with date, location and photos; track beehive treatments and withdrawal periods.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "check whether AI crawlers can read a website", the likely first call is audit_website.

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: 3, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it1 of 3 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer352 ms
  • Space in an agent's context≈ 119 tokensthe definitions of all its tools (1), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 1 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 1 of 1

What an agent can do with it

  • can do · check whether AI crawlers can read a website
  • cannot · record fishing catches with date, location and photos
  • cannot · track beehive treatments and withdrawal periods

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 offers1 tools · read 2026-10-24
  • audit_website

    Audit whether AI crawlers may read a site and whether AI search can cite it. Checks robots.txt bot rules (GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot …), llms.txt, JSON-LD, meta tags and sitemap. Returns…

How to connect

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

{
  "mcpServers": {
    "audit": {
      "type": "http",
      "url": "https://ai-visibility.rowb.app/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http rowb https://ai-visibility.rowb.app/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://ai-visibility.rowb.app/mcp as a custom connector in the settings.

Other servers listed as rowb's
  • app.rowb.auth-posture/auditanswers, 1 toolsverified in the MCP registry
  • app.rowb.catchlog/logbookanswers, 3 toolsverified in the MCP registry
  • app.rowb.caz-cost/zonesnot asked yetverified in the MCP registry
  • app.rowb.dubai-log/uae-costsnot asked yetverified in the MCP registry
  • app.rowb.gbu-compliance/assessmentnot asked yetverified in the MCP registry
  • app.rowb.hive-ledger/rotationnot asked yetverified in the MCP registry
  • app.rowb.hk-transit/faresnot asked yetverified in the MCP registry
  • app.rowb.hourproof/hoursnot asked yetverified in the MCP registry
  • app.rowb.ladder/boardnot asked yetverified in the MCP registry
  • app.rowb.mcp-health/probenot asked yetverified in the MCP registry
  • app.rowb.mcp-scan/weeklynot asked yetverified in the MCP registry
  • app.rowb.oganvil/og-image-apinot asked yetverified in the MCP registry
  • app.rowb.pool-log/water-lognot asked yetverified in the MCP registry
  • app.rowb.prices/indexnot asked yetverified in the MCP registry
  • app.rowb.registry-lag/reflectionnot asked yetverified in the MCP registry
  • app.rowb.septic-log/maintenancenot asked yetverified in the MCP registry
  • app.rowb.sg-parking-live/carpark-availabilitynot asked yetverified in the MCP registry
  • app.rowb.stampcard/cardsnot asked yetverified in the MCP registry

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.