read
AI agents call read to retrieve information from MCP Claude Code without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'read' combined with its position among file manipulation tools (edit, content_replace, multi_edit) strongly indicates a data retrieval operation. Without a description, confidence is slightly reduced, but the naming is unambiguous. Read operations have minimal blast radius even if misused by an AI agent, hence low severity.
From the tool's definition Tool named 'read' with no description provided. Based on naming convention and context as a sibling to 'edit', 'content_replace', and other file operation tools on a code analysis server, 'read' almost certainly retrieves file contents without modification.
Attacks that exploit this kind of access
read. It is categorised as a Read tool in the MCP Claude Code MCP Server, which means it retrieves data without modifying state.
Register the MCP Claude Code MCP server in PolicyLayer and add a rule for read: 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 MCP Claude Code. Nothing to install.
read 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 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. 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 is provided by the MCP Claude Code MCP server (sdglbl/mcp-claude-code). 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 →