List files and directories within allowed roots. Use this to discover files without requiring full absolute paths from the user.
AI agents call read_directory to retrieve information from Documcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs directory enumeration/listing, which is a read-only information retrieval operation with no side effects. It discovers file structure but does not create, modify, delete, or execute anything. The scope is limited to "allowed roots," further constraining potential impact. This is a standard file exploration utility appropriate for documentation analysis workflows.
From the tool's definition Tool description states "List files and directories" which is a retrieval operation. The name "read_directory" and verb "List" indicate querying directory contents without modification.
Documented attack patterns abuse exactly the kind of access read_directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Documcp, and nothing reaches the server without passing your rules. This is the rule we recommend for read_directory:
{
"version": "1",
"default": "deny",
"tools": {
"read_directory": {}
}
}read_directory 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.
List files and directories within allowed roots. Use this to discover files without requiring full absolute paths from the user. It is categorised as a Read tool in the Documcp MCP Server, which means it retrieves data without modifying state.
Register the Docu MCP server in PolicyLayer and add a rule for read_directory: 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 Documcp. Nothing to install.
read_directory 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 read_directory 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 read_directory. 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.
read_directory is provided by the Docu MCP server (tosin2013/documcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Documcp, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
52 Documcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.