AI agents call docs_list to retrieve information from Docs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists documentation file paths from locally installed packages. It is a pure query operation with no side effects, no code execution, no data modification, and no external operations triggered. It serves solely to enumerate available documentation, which is a read-only action.
From the tool's definition Tool name 'docs_list' and description 'List doc file paths' with optional package filtering. No modification, deletion, or execution capability. Returns paths for use with docs_read.
Attacks that exploit this kind of access
List doc file paths. Each entry is the path you pass to docs_read. Optionally filter to one package. It is categorised as a Read tool in the Docs MCP Server, which means it retrieves data without modifying state.
Register the Docs MCP server in PolicyLayer and add a rule for docs_list: 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 Docs. Nothing to install.
docs_list 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 docs_list 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 docs_list. 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.
docs_list is provided by the Docs MCP server (particle-academy/docs-mcp). 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 →