AgentGrade

com.agentgrade/mcp-server

This is a diagnostic tool for the emerging ecosystem of AI-accessible web services. It scans URLs for agent-specific protocols like x402, MPP, L402, and discovery endpoints, then returns Lighthouse-style reports grading a site's readiness for programmatic access by AI agents. You get four tools: a full scan with comprehensive protocol detection, a compact version returning just capabilities and a numeric score, history lookups if you've configured a database, and a standalone x402.json validator. Reach for this when you're building agent workflows and need to quickly assess whether a target site exposes machine-readable payment rails, service definitions, or structured discovery metadata before attempting integration.

tools: 4
transport: HTTP
last updated: Apr 12, 2026

Open website

Install

From registry metadata

$ npx add-mcp https://agentgrade.com/mcp --name agentgrade

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http agentgrade https://agentgrade.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 4 tools

Verified live against the running server on Nov 6, 2026.

scan_urlScan a URL for agent capabilities and payment protocols. Returns full results including x402, MPP, L402, discovery, bazaar, MCP, plugins, OpenAPI, and more.1 params

Scan a URL for agent capabilities and payment protocols. Returns full results including x402, MPP, L402, discovery, bazaar, MCP, plugins, OpenAPI, and more.

Parameters* required

url*string

URL to scan (http or https)

scan_compactCompact scan returning only rails, capabilities, and a numeric score. Optimized for agent decision-making.1 params

Compact scan returning only rails, capabilities, and a numeric score. Optimized for agent decision-making.

Parameters* required

url*string

URL to scan

get_historyGet scan history for a URL. Requires database to be configured.2 params

Get scan history for a URL. Requires database to be configured.

Parameters* required

limitnumber

Max results (default 20, max 100)

urlstring

Filter by URL (optional)

validate_x402_jsonValidate x402.json content against expected schema. Returns errors, warnings, and suggestions. No network requests — pure validation.1 params

Validate x402.json content against expected schema. Returns errors, warnings, and suggestions. No network requests — pure validation.

Parameters* required

content*object

The x402.json content to validate

Details

Categories: AI & LLM Tools, Finance & Commerce
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related AI & LLM Tools MCP servers

View all

Arbiturowritan-labs/arbituro-mcpWork Arbituro jobs from a coding agent: read the done-when, link the PR, claim what you checked.0stars

AY Inboxayinbox/ayinbox-mcpCold email from your agent: contact lists, campaigns, campaign brains, reply drafts and a CRM.0stars

Blackwallbluetieroperations-create/blackwall-mcpAPI-key pre-action risk gate: any irreversible agent action (money, SQL, delete, email).0stars

Autobrowserapproval Mcpclauxel/autobrowser-approval-cloud-mcpA paid remote MCP for AI agent browser approval MCP, built to return verdicts, receipts, usage logs,0stars

Chromedevtoolsmcp Mcpclauxel/chrome-devtools-session-mcp-mcpA paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,0stars

Jcodeharness Mcpclauxel/jcode-harness-cloud-mcpA paid remote MCP for OpenAI Codex harness MCP, built to return verdicts, receipts, usage logs, and0stars