AI agents call list_docs to retrieve information from Astrolabe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'list_docs' strongly suggests it returns a list of available documents, a read-only query operation with no side effects. Although the description is empty, the naming pattern and sibling tools (all read operations) confirm this is a retrieval/discovery tool. No data is modified, deleted, or executed. The blast radius of misuse is minimal—an agent would only discover what documents exist.
From the tool's definition Tool name 'list_docs' indicates enumeration of documentation; sibling tools like 'search_docs', 'read_doc', 'get_card', 'get_cosmos' are all read-only retrieval operations, establishing context that this server focuses on documentation discovery and retrieval…
Attacks that exploit this kind of access
list_docs. It is categorised as a Read tool in the Astrolabe MCP Server, which means it retrieves data without modifying state.
Register the Astrolabe MCP server in PolicyLayer and add a rule for list_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 Astrolabe. Nothing to install.
list_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 list_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 list_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.
list_docs is provided by the Astrolabe MCP server (zebrr/astrolabe-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 →