AI & Machine Learning
agentklarity.com
Runs live Agent-Readiness audits against websites, scoring crawlability, accessibility, readability, and executability for AI agents.
ENDPOINT 1
https://agentklarity.com/mcp
MCP server metadata
- Name
- Agent Klarity
- Version
- 1.0.0
Known tools 3
about_klarityWhat Agent Klarity is, what it does, and how to reach it -- the same facts a human would find on the homepage.
Inferred read-onlyrun_agent_readiness_auditRuns a live Agent-Readiness audit (Agent Klarity's CARE framework: Crawlability, Accessibility, Readability, Executability) against a given website URL and returns its 0-100 score, band, layer breakdown, and top findings.
Inferred read-onlylist_blog_postsLists Agent Klarity's blog posts -- research and product notes on making a website usable by AI agents.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.agent-klarity]
url = "https://agentklarity.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"agent-klarity": {
"type": "http",
"url": "https://agentklarity.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: agent-klarity
Remote MCP URL: https://agentklarity.com/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"agent-klarity": {
"url": "https://agentklarity.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"agent-klarity": {
"type": "http",
"url": "https://agentklarity.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "agent-klarity",
"transport": "streamable-http",
"url": "https://agentklarity.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.