Agenttrust runs on your own machine — the client starts it, so there is no endpoint to ping. 26 installs a week from npm. Last commit 13 May 2026.
Trust scores & reputation for the agent-to-agent economy. Verify A2A counterparties.
Today is the operative word: we check Agenttrust every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add agenttrust -- npx -y agenttrust-mcp
{
"mcpServers": {
"agenttrust": {
"args": [
"-y",
"agenttrust-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agenttrust]
command = "npx"
args = ["-y", "agenttrust-mcp"]
{
"mcpServers": {
"agenttrust": {
"args": [
"-y",
"agenttrust-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agenttrust": {
"args": [
"-y",
"agenttrust-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENTTRUST_API_KEY (API key for write operations. Reads are public. Free tier: 100 writes/day.), AGENTTRUST_API_BASE (Override the API base URL for self-hosted deployments.).
The author declared them in the registry entry; get the values from the project itself.
MCP Server for Agent Reputation & Trust Scoring
Decay-weighted reputation + tamper-evident trust attestations for the agent economy.
Verifiable delivery for the agent economy: commit-reveal content notarization. Sellers commit to a d
Is this address safe to pay? OFAC sanctions, ERC-8004 reputation, contract analysis.
Reputation scoring for AI agent wallets on Base. Trust scores, fraud checks, x402.
The wallet an AI agent carries — mandate, budget, vault, and audit. Counterparties verify first.
Counterparty risk transfer for the agent economy: agents post bonds behind their promises, wronged c
MCP server quality scoring and optimization for the agent economy.
Answers built from our own checks of this server.