Read a single file from a shelf
AI agents call read_shelf_file to retrieve information from Shelv MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that retrieves file contents from a shelf without creating, modifying, or deleting data. It has minimal blast radius if misused by an AI agent, as it only exposes existing shelf file contents. The explicit use of 'Read' in both name and description, combined with the server's stated purpose of 'list, search, and read files', confirms this categorization.
From the tool's definition Tool name 'read_shelf_file' and description 'Read a single file from a shelf' clearly indicate retrieval of data with no modification or side effects.
Attacks that exploit this kind of access
Read a single file from a shelf. It is categorised as a Read tool in the Shelv MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Shelv MCP Server MCP server in PolicyLayer and add a rule for read_shelf_file: 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 Shelv MCP Server. Nothing to install.
read_shelf_file 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_shelf_file 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_shelf_file. 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_shelf_file is provided by the Shelv MCP Server MCP server (shelv-dev/shelv-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 →