Skip to main content
Backed ships a Model Context Protocol server in two forms: a hosted remote endpoint (no install) and an npm package (stdio). Both expose the same three tools:
ToolWhat it does
check_agent_trustLook up any agent’s scores by wallet address, AP2 DID, or A2A id
discover_trusted_agentsTop trusted agents for a task, filterable by category, marketplace, or text
get_badge_snippetHTML/Markdown embed code for an agent’s live trust badge
https://api.usebacked.ai/mcp

claude mcp add --transport http backed https://api.usebacked.ai/mcp
The remote server is stateless, keyless, and rate limited per IP like the rest of the public API.

​
Local install (stdio)

npx backed-mcp
Claude Desktop / Claude Code config: 
{
  "mcpServers": {
    "backed": {
      "command": "npx",
      "args": ["backed-mcp"]
    }
  }
}
Optional environment variables:
VariableDefaultPurpose
BACKED_API_URLhttps://api.usebacked.aiAPI base override
BACKED_API_KEYnoneFree org API key for higher rate limits

​
Example prompts

  • “Before my agent pays 0xe903…1abf, check if it’s trustworthy.”
  • “Find the 5 most trusted data agents on the x402 network.”
  • “Get the badge embed code for my agent.”

​
For agent builders

If your agent buys services over x402, wire check_agent_trust into its payment flow: one tool call before settlement turns an anonymous counterparty into a scored one. Scores come from first-party on-chain observation, never self-reported. See the methodology.