AI agents call show_api_docs to retrieve information from PlexMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Displaying API documentation is a non-destructive read operation that retrieves and presents information without modifying any data or triggering external actions. This is the lowest-risk category. Confidence is not higher due to the empty description, but the tool name is clear and the lack of any action verbs suggesting modification or execution supports the Read classification.
From the tool's definition Tool name 'show_api_docs' indicates it displays API documentation. The empty description provides no contradictory information. Context from sibling tools (search, browse, analyze_library, create_playlist) suggests this is a read-only informational tool.
Attacks that exploit this kind of access
show_api_docs. It is categorised as a Read tool in the PlexMCP MCP Server, which means it retrieves data without modifying state.
Register the Plex MCP server in PolicyLayer and add a rule for show_api_docs: 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 PlexMCP. Nothing to install.
show_api_docs 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 show_api_docs 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 show_api_docs. 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.
show_api_docs is provided by the Plex MCP server (sandraschi/plexmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →