AgentTrust runs on your own machine — the client starts it, so there is no endpoint to ping. 150 installs a week from pypi. Last commit 22 Mar 2026.
MCP Server for Agent Reputation & Trust Scoring
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 agent-trust -- uvx agent-trust-mcp
{
"mcpServers": {
"agent-trust": {
"args": [
"agent-trust-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.agent-trust]
command = "uvx"
args = ["agent-trust-mcp"]
{
"mcpServers": {
"agent-trust": {
"args": [
"agent-trust-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"agent-trust": {
"args": [
"agent-trust-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
DATABASE_URL (PostgreSQL asyncpg connection string), REDIS_URL (Redis connection string), SIGNING_KEY_PATH (Path to Ed25519 private key PEM file), AUTH_PROVIDER (Authentication provider: agentauth | standalone | both (default: both)), AGENTAUTH_ACCESS_TOKEN (Access token for AgentAuth MCP tool calls).
The author declared them in the registry entry; get the values from the project itself.
MCP server quality scoring and optimization for the agent economy.
Reputation scoring for AI agent wallets on Base. Trust scores, fraud checks, x402.
Portable reputation for AI agents. MCP-native identity, vouching, trust scores.
Agent reputation scoring: trust scores, Sybil detection, cross-chain identity for 133K+ agents
Recraft AI Image Generation MCP Server for AI coding agents
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
MCP server for browser automation with AI agent
Answers built from our own checks of this server.