Koskamo

Agent Ready MCP

An MCP server that allows AI agents to scan websites and evaluate their readiness for AI interaction. It provides a score out of 100, grades, area-specific scores, key findings, and links to full reports with fix plans. The server uses public scanning via AgentReadyBot and requires no sign-in or API key.

Visit Sneeze It

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Agent Ready MCP logo, by Sneeze ItVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Sneeze It
MCP endpoint (Streamable HTTP)
https://agentready.sneeze.it/mcp
Vendor documentation

What you can do with it

  • Scan a website to check AI agent readiness
  • Get a detailed report with scoring and findings
  • Explain specific scoring checks
  • Retrieve the scoring methodology

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: it.sneeze.agentready/agent-ready@1.0.0Project website

Protocol and capabilities

Server
agent-ready 1.0.0
MCP protocol
2025-06-18
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Agent Ready scores whether AI agents can use a website. Use scan_website when someone asks whether a site works with AI agents, ChatGPT, Claude or Gemini, or how to make it agent ready. Present the score, the weakest areas and their findings, and give the report link for the full fix plan. Scores are out of 100; areas with nothing to measure are left out rather than scored zero.

Tools

4 advertised

scan_website — Scan a website for agent readiness
Advertised by the server during the last successful anonymous check.
Open-world

Score any public website out of 100 for how well AI agents can use it: reach it, understand it, act on it (book, quote, buy), complete the task, act for a signed-in customer, trust its facts, and find the right location. Returns the score, a score per area, the most important finding in each area, and a link to the full report with every finding and the ordered fix plan. Takes 5 to 20 seconds.

scan_website input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The website to scan, for example acme.com or https://www.acme.com/"
    },
    "fresh": {
      "type": "boolean",
      "description": "Rescan even if the site was scanned in the last 30 minutes. Use after the owner changed something."
    }
  }
}
scan_website annotations
{
  "title": "Scan a website for agent readiness",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
get_report — Get an existing Agent Ready report
Advertised by the server during the last successful anonymous check.
Advertised read-only

Fetch a report that was already run, by its report link or id, without scanning again.

get_report input schema
{
  "type": "object",
  "required": [
    "report"
  ],
  "properties": {
    "report": {
      "type": "string",
      "description": "A report URL (https://agentready.sneeze.it/report/...) or report id."
    }
  }
}
get_report annotations
{
  "title": "Get an existing Agent Ready report",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
explain_check — Explain one Agent Ready check
Advertised by the server during the last successful anonymous check.
Advertised read-only

Explain what one check measures, what it is worth and where to read how to fix it. Pass the check name as it appears in a report, for example "WebMCP tools an agent can call".

explain_check input schema
{
  "type": "object",
  "required": [
    "check"
  ],
  "properties": {
    "check": {
      "type": "string",
      "description": "The check name, or a few words from it."
    }
  }
}
explain_check annotations
{
  "title": "Explain one Agent Ready check",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
get_scoring_method — How the Agent Ready score works
Advertised by the server during the last successful anonymous check.
Advertised read-only

The scored areas, their weights and every check, so a score can be explained.

get_scoring_method input schema
{
  "type": "object",
  "properties": {}
}
get_scoring_method annotations
{
  "title": "How the Agent Ready score works",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
425 ms
95th percentile latency
425 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 425 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http agent-ready-mcp-sneeze https://agentready.sneeze.it/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add agent-ready-mcp-sneeze --url https://agentready.sneeze.it/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agent-ready-mcp-sneeze in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agent-ready-mcp-sneeze": {
      "url": "https://agentready.sneeze.it/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agent-ready-mcp-sneeze": {
      "type": "streamableHttp",
      "url": "https://agentready.sneeze.it/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agent-ready-mcp-sneeze and inspect its tools.
VS Code configuration
{
  "servers": {
    "agent-ready-mcp-sneeze": {
      "type": "http",
      "url": "https://agentready.sneeze.it/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http agent-ready-mcp-sneeze https://agentready.sneeze.it/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "agent-ready-mcp-sneeze": {
      "url": "https://agentready.sneeze.it/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agent-ready-mcp-sneeze": {
      "serverUrl": "https://agentready.sneeze.it/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Agent Ready MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 3,712

Do you run Agent Ready MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing