Reputation Management
Reputation usage in MCP-I
Reputation Management
Building on audit data, MCP-I enables reputation management for agents:
Reputation Components
- Trust Score: A numeric representation of an agent's trustworthiness
- Behavior Analysis: Patterns of agent requests and activities
- Verification History: Success and failure rates of credential verification
- Feedback Mechanisms: Reports from services or principals
Reputation is derived from:
Reputation is exposed downstream for MCP-I Aware services.
- Number of successful verifications
- Past revocations
- Scope of delegated actions
KnowThat.ai Registry
The canonical public registry at KnowThat.ai provides:
- Agent Directory: Searchable registry of known agents
- Reputation API: Query agent reputation information
- Flagging System: Mark problematic agents or behaviors
- Conformance Badges: Display MCP-I conformance levels
Implementation Example
// Example reputation check implementation
async function checkAgentReputation(agentDid) {
try {
// Query the reputation service
const response = await fetch(
`https://api.knowthat.ai/reputation/${encodeURIComponent(agentDid)}`
);
if (!response.ok) {
throw new Error(`Reputation check failed: ${response.status}`);
}
const reputation = await response.json();
// Apply reputation-based policy
if (reputation.score < 50) {
console.warn(`Low reputation agent detected: ${agentDid}`);
// Implement additional verification or restrictions
}
// Log the reputation check
await logAuditEvent({
eventType: "ReputationChecked",
actorId: agentDid,
result: {
reputationScore: reputation.score,
reputationFlags: reputation.flags,
},
});
return reputation;
} catch (error) {
console.error("Reputation check error:", error);
// Fall back to default policy
return { score: 0, flags: ["unknown"], error: error.message };
}
}