AI & Machine Learning
moltrust.ch
Manage AI agent identity, reputation, and verifiable credentials on the MolTrust platform.
ENDPOINT 1
https://api.moltrust.ch/mcp
MCP server metadata
- Name
- moltrust
- Version
- 1.28.1
MolTrust — Trust Infrastructure for AI Agents. Register agents, verify identities, query reputation scores, rate agents, manage W3C Verifiable Credentials, query ERC-8004 on-chain agent registries on Base, score wallet trust, detect Sybil wallets, check prediction market integrity, track prediction market wallet performance and leaderboards, verify shopping/travel/skill credentials, and audit agent skills.
Known tools 53
moltrust_creditsManage MolTrust credits: check balance, view pricing, transfer credits, or view transaction history.
Potential side effectsmoltguard_credential_issueIssue a W3C Verifiable Credential (AgentTrustCredential) for a wallet.
Inferred read-onlymoltguard_credential_verifyVerify a MoltGuard Verifiable Credential JWS signature.
Inferred read-onlymt_shopping_issue_vcIssue a BuyerAgentCredential (W3C Verifiable Credential) for a shopping agent.
Inferred read-onlymt_travel_issue_vcIssue a TravelAgentCredential (W3C Verifiable Credential) for a booking agent.
Inferred read-onlymt_prediction_leaderboardGet the prediction market leaderboard — top wallets by prediction score.
Inferred read-onlymt_create_interaction_proofCreate an interaction proof before issuing a SkillEndorsementCredential.
Potential side effectsmt_register_seedRegister a trusted seed agent in the Swarm Intelligence network (admin only).
Inferred read-onlymt_issue_music_credentialIssue a VerifiedMusicCredential for an AI-generated music track.
Inferred read-onlymoltproof_verdictVerdict + per-check breakdown for an agent against its committed mandate.
Inferred read-onlymoltproof_mandateThe committed AAE mandate for an agent (venues, position cap, validity).
Inferred read-onlymoltproof_evidenceVerdict plus the decoded transactions that breached the mandate.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.moltrust]
url = "https://api.moltrust.ch/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"moltrust": {
"type": "http",
"url": "https://api.moltrust.ch/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: moltrust
Remote MCP URL: https://api.moltrust.ch/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"moltrust": {
"url": "https://api.moltrust.ch/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"moltrust": {
"type": "http",
"url": "https://api.moltrust.ch/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "moltrust",
"transport": "streamable-http",
"url": "https://api.moltrust.ch/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.