Retrieve plugin adapter source code for security review. Call this before enabling an unreviewed plugin.
AI agents call plugin_inspect to retrieve information from OpenTabs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves source code for inspection without side effects. It is a defensive security measure to allow users to audit plugins before enabling them. The action is non-destructive, non-executable, and informational in nature, making it a straightforward Read classification with low severity.
From the tool's definition Tool description states 'Retrieve plugin adapter source code' — a read-only operation that fetches and displays code for review purposes. No modification, execution, or deletion of data occurs.
Documented attack patterns abuse exactly the kind of access plugin_inspect gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenTabs, and nothing reaches the server without passing your rules. This is the rule we recommend for plugin_inspect:
{
"version": "1",
"default": "deny",
"tools": {
"plugin_inspect": {}
}
}plugin_inspect 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.
Retrieve plugin adapter source code for security review. Call this before enabling an unreviewed plugin. It is categorised as a Read tool in the OpenTabs MCP Server, which means it retrieves data without modifying state.
Register the OpenTabs MCP server in PolicyLayer and add a rule for plugin_inspect: 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 OpenTabs. Nothing to install.
plugin_inspect 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 plugin_inspect 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 plugin_inspect. 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.
plugin_inspect is provided by the OpenTabs MCP server (opentabs-dev/opentabs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 OpenTabs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 OpenTabs tools catalogued and risk-classified — across an index of 42,500+ MCP servers.