Read a text file inside an allowed project root.
AI agents call mcp_read_file to retrieve information from Local Code without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file content from restricted directories (allowed project roots) without any side effects, mutations, or external operations. It is a straightforward read operation with minimal risk, especially given the access control constraint. The low severity reflects that unauthorized data exposure is the only concern, mitigated by the allowlist mechanism.
From the tool's definition Tool name 'mcp_read_file' and description 'Read a text file inside an allowed project root' explicitly indicate retrieval of file content with no modification capability.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Read a text file inside an allowed project root. It is categorised as a Read tool in the Local Code MCP Server, which means it retrieves data without modifying state.
Register the Local Code MCP server in PolicyLayer and add a rule for mcp_read_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 Local Code. Nothing to install.
mcp_read_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 mcp_read_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 mcp_read_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.
mcp_read_file is provided by the Local Code MCP server (js190-prog/local-code-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 →