check_trust

A read tool on the AgentVeil Protocol MCP server.

SERVERAgentVeil Protocol SOURCEagentveil-protocol/agentveil-sdk

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade A, identity unverified Pull the record →

This record as markdown: /tools/agentveil-protocol-agentveil-sdk/check-trust.md

WHAT IT DOES

What check_trust does on AgentVeil Protocol

AI agents call check_trust to retrieve information from AgentVeil Protocol without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why check_trust is rated Low

The tool is almost certainly a read operation that queries trust or reputation information about agents in the AgentVeil Protocol. Given the server's purpose (trust and reputation infrastructure) and the naming pattern of related tools, this appears to be a lookup/retrieval function. The empty description reduces confidence slightly, but contextual evidence strongly suggests read-only behavior.

From the tool's definition Tool name 'check_trust' suggests retrieval of trust/reputation data; no description provided. Context from sibling tools ('check_avp_reputation', 'check_reputation', 'get_agent_info', 'get_attestations_received', 'get_audit_trail') indicates this server…

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs check_trust safely

PolicyLayer is an MCP gateway: it sits between your AI agents and AgentVeil Protocol, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For check_trust, this is the rule to start with:

check_trust Allowed

check_trust is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "check_trust": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect AgentVeil Protocol, apply this rule, and every check_trust call is checked against it from then on.

FAQ

Questions about check_trust

What does the check_trust tool do? +

check_trust is a read tool on the AgentVeil Protocol MCP server. It is categorised as a Read tool in the AgentVeil Protocol MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on check_trust? +

Register the AgentVeil Protocol MCP server in PolicyLayer and add a rule for check_trust: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches AgentVeil Protocol. Nothing to install.

What risk level is check_trust? +

check_trust is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit check_trust? +

Yes. Add a rate_limit block to the check_trust rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block check_trust completely? +

Set action: deny in the PolicyLayer policy for check_trust. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides check_trust? +

check_trust is provided by the AgentVeil Protocol MCP server (agentveil-protocol/agentveil-sdk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on AgentVeil Protocol, and thousands of servers like it.

This server

All 12 AgentVeil Protocol tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →