Use SLA.directory with AI

Ask your AI assistant about SLAs in plain language: uptime commitments, service credits, claim windows, and per-service guarantees. Answers come from the same verified data behind this site, and they cite the source.

SLA.directory ships an MCP server ↗ that connects the public API to assistants like Claude and Cursor.

🔌 One config blockAdd a few lines to Claude Desktop or Cursor and you are connected.

✅ Verified dataBacked by the same data and API that power this site.

🔗 Cited answersResponses point back to the vendor and the source on SLA.directory.

Add the MCP server

The server is published as the sla-directory-mcp npm package and runs over stdio. Paste this into your assistant's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: mcpServers in settings):

// mcpServers configuration
{
  "mcpServers": {
    "sla-directory": {
      "command": "npx",
      "args": ["-y", "sla-directory-mcp"]
    }
  }
}

Heads up: sla-directory-mcp is not on npm yet, so the npx command above will work once it is published. To try it today, run it from source: clone github.com/self9dmin/sla-mcp ↗, then run npm install && npm run build && node dist/index.js, and point your assistant's command at that node dist/index.js invocation.

Add to Cursor MCP server repo ↗

Example prompts

Once connected, ask questions like these:

What is AWS S3's SLA?

Compare Stripe, Adyen, and PayPal SLA credits for a renewal.

Which security vendors offer automatic credits?

What are Azure's weakest-SLA services?

How it works

The MCP server is a thin client over the public SLA.directory API. Your assistant calls it to look up vendors, services, credit tiers, and claim processes, then answers in plain language with a link back to the source. No account, no API key, no rate limits.

Browse the endpoints on the API page.
Read the full schema in the interactive API reference ↗.
Pull every vendor at once from /api/v1/vendors/full.json.
See the server code at github.com/self9dmin/sla-mcp ↗.