Koskamo

AgentGauge MCP

AgentGauge is a public MCP server that allows AI agents to scan any website and grade its readiness for AI agents. It evaluates whether an agent can discover, understand, trust, and transact with a site against the AgentReady standard. The server exposes a single tool, scan_website, which requires no authentication and provides an instant letter grade.

Visit AgentGauge

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.

AgentGauge MCP logo, by AgentGaugeCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by AgentGauge
MCP endpoint (Streamable HTTP)
https://mcp.agentgauge.ai/mcp
Vendor documentation

What its tools do

1 tool, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (1)

1 of 1 have a description · 0 of 1 declare behavior hints · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Scan any website URL for AI readiness
  • Grade AI search visibility and agent usability
  • Check if agents can discover and trust a site

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.GlassCaseOfEmotion/agentgauge@1.0.0Source repository
Maintenance checked

Protocol and capabilities

Server
agentgauge 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
1 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

1 advertised

scan_website — Scan a website for AI readiness
Advertised by the server during the last successful anonymous check.

Run an AgentGauge agent-readiness scan of a website. Grades whether AI search can find/cite it and whether AI agents can use/transact with it, against the AgentReady standard. Returns the grade, both gauges, every check with its status, and a link to the full report.

scan_website input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The website URL or domain to scan, e.g. \"example.com\""
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

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
1479 ms
95th percentile latency
1479 ms

Maintenance history

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

  • · probe · passed · 1479 ms · metadata changed · 1 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 agentgauge-mcp https://mcp.agentgauge.ai/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 agentgauge-mcp --url https://mcp.agentgauge.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agentgauge-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agentgauge-mcp": {
      "url": "https://mcp.agentgauge.ai/mcp"
    }
  }
}

Cline

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

VS Code

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

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://mcp.agentgauge.ai/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": {
    "agentgauge-mcp": {
      "serverUrl": "https://mcp.agentgauge.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AgentGauge 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 8,304