AI agents call list_documentation to retrieve information from TheAlmanac without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about available documentation without creating, modifying, deleting, or executing any operations. It is a pure read operation with minimal security risk. Even if an AI agent calls it, the worst outcome is receiving a list of available resources, which is informational only.
From the tool's definition Tool name 'list_documentation' and description 'List available documentation sources or documents' indicate a retrieval operation with no modification or execution of code.
Documented attack patterns abuse exactly the kind of access list_documentation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TheAlmanac, and nothing reaches the server without passing your rules. This is the rule we recommend for list_documentation:
{
"version": "1",
"default": "deny",
"tools": {
"list_documentation": {}
}
}list_documentation 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 available documentation sources or documents. It is categorised as a Read tool in the TheAlmanac MCP Server, which means it retrieves data without modifying state.
Register the TheAlmanac MCP server in PolicyLayer and add a rule for list_documentation: 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 TheAlmanac. Nothing to install.
list_documentation 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 list_documentation 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 list_documentation. 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.
list_documentation is provided by the TheAlmanac MCP server (saharcarmel/thealmanac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TheAlmanac, 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.
5 TheAlmanac tools catalogued and risk-classified — across an index of 43,000+ MCP servers.