Trust
Trust layer for AI agents: identity, guard, redact, escrow, and x402 payments.
Connector by agntor · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/agntor-trust
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 9 read · 2 write · 1 delete · 2 not yet classified
- Secrets
- 2 (API keys, tokens or passwords)
- Install scripts
- Not scanned yet
- Runs as
- Node.js package
Tools by what they do 14
Read from the source code; the running server may list different tools.
Read 9 · Look things up without changing anything.
check_agent_pulseget_agent_cardget_agent_registrationget_trust_scoreguard_inputis_agent_certifiedissue_audit_ticketquery_agentsredact_output
Write 2 · Create, change, send or run things.
create_escrowregister_agent
Delete 1 · Delete, drop, revoke or wipe things.
activate_kill_switch
Not yet classified 2 · We could not tell from the name and description.
guard_toolverify_agent_identity
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
AGNTOR_API_KEYAGNTOR_SECRET_KEY
Tools (14)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
activate_kill_switchActivate Kill SwitchEmergency disable an agent
check_agent_pulseCheck Agent PulseGet real-time health and behavioral metrics
create_escrowCreate EscrowCreate a new escrow task for payment
get_agent_cardGet Agent CardRetrieve the verifiable AgentCard (Passport) for an agent
get_agent_registrationGet Agent RegistrationRetrieve the EIP-8004 agent registration file
get_trust_scoreGet Agent Trust ScoreCalculate comprehensive trust score with behavioral factors
guard_inputGuard InputScan incoming prompts for unsafe or malicious instructions
guard_toolGuard ToolAuthorize or block tool execution
is_agent_certifiedCheck Agent CertificationVerify if an agent has valid Agntor certification
issue_audit_ticketIssue Audit TicketGenerate signed JWT ticket for x402 transactions
query_agentsQuery AgentsSearch for agents by criteria
redact_outputRedact OutputScan and redact sensitive content from outputs
register_agentRegister AgentRegister a new AI agent in the Agntor trust network
verify_agent_identityVerify Agent IdentityTrigger self-verification via SDK
Signals
- Stars
- 1
- Forks
- 3
- Open issues
- 0
- Weekly downloads
- 11
- Last commit
- Feb 16, 2026 (8 months ago)
- Last release
- Feb 16, 2026 (8 months ago)
- Last package publish
- Feb 16, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.agntor/trust- Version
- 0.1.0
- Auth
- API key
- Packages
- npm @agntor/mcp
- License
- MIT
- Repository
- github.com/agntor/mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 25, 2026
Cite this page
Trust MCP server. Agent Mart. https://agentmart.dev/connectors/agntor-trust (last updated 2026-10-25)