Side-by-Side Model Context Protocol Comparison
Agent Ready MCP vs Fleets
In-depth architectural comparison of the Agent Ready MCP and Fleets MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Agent Ready MCP
Cloud Platforms · Local stdio
Quality: 51/100 (Good) | Auth: No auth required
Fleets
Cloud Platforms · Local stdio
Quality: 52/100 (Good) | Auth: No auth required
Verdict Summary: Choose Agent Ready MCP if you need specialized Cloud Platforms tools running via a local process. Choose Fleets if your workspace requires Cloud Platforms integration with local subprocess execution. Both servers can be configured concurrently in your client's
mcpServers manifest.Which MCP Server Should You Choose?
Choose Agent Ready MCP when:
- You need dedicated capabilities in the Cloud Platforms domain.
- You prefer local stdio subprocess transport architecture.
- Your security boundary fits: No auth required (Free / Open Source).
- Primary tools included: scan_site, get_scan, ask.
Choose Fleets when:
- You need dedicated capabilities in the Cloud Platforms domain.
- You prefer local stdio subprocess transport architecture.
- Your security boundary fits: No auth required (Free / Open Source).
- Primary tools included: list_sites, stats, funnel.
Feature & Specification Comparison
Tools & Capabilities Breakdown
Agent Ready MCP Tools (4)
scan_site
Scan object: Vercel score 0–100, llms.txt sub-score 0–100, per-check findings with `howToFix` strings. Keyless runs use the anonymous free tier (3 scans/30 days per IP) and return synchronously; with a Pro key, returns `{ id, status: "running" }` placeholder if the scan exceeds the poll deadline.
get_scan
Same scan object as `scan_site`, or `not_found` if the id is unknown or doesn't belong to the authenticated user. Pro key required.
ask
NLWeb `/ask` over Agent Ready's methodology, checks, and specs. Public — no API key required. Schema.org-typed result objects.
validate_structured_data
D-series structured-data result: `mode`, `url`, per-check findings, and a `summary` verdict. Public — no API key required. Validates schema lint + agent-coherence the first-party validators don't.
Fleets Tools (8)
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Agent Ready MCP Configuration
Fleets Configuration