AI agents call providers.items to retrieve information from Executor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about credential providers. While credential data is sensitive, 'browse' implies read-only access to metadata rather than exposing secrets themselves. The low severity reflects that browsing provider configurations has minimal blast radius if misused by an agent—it gathers information but does not create, modify, delete, or execute operations.
From the tool's definition The tool name 'providers.items' and description 'Browse a credential provider' indicate a read-only operation that retrieves or lists information about credential providers.
Documented attack patterns abuse exactly the kind of access providers.items gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Executor, and nothing reaches the server without passing your rules. This is the rule we recommend for providers.items:
{
"version": "1",
"default": "deny",
"tools": {
"providers.items": {}
}
}providers.items is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Browse a credential provider. It is categorised as a Read tool in the Executor MCP Server, which means it retrieves data without modifying state.
Register the Executor MCP server in PolicyLayer and add a rule for providers.items: 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 Executor. Nothing to install.
providers.items is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the providers.items 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.
Set action: deny in the PolicyLayer policy for providers.items. 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.
providers.items is provided by the Executor MCP server (rhyssullivan/executor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 29 Executor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
29 Executor tools catalogued and risk-classified — across an index of 42,500+ MCP servers.