read_file_full
AI agents call read_file_full to retrieve information from Portable MCP Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file contents for code analysis purposes. It performs a query operation (read) on existing data with no modification, deletion, or execution. The empty description reduces specificity slightly, but the name and server context (semantic code search, pattern analysis) clearly indicate a read-only function.
From the tool's definition Tool name 'read_file_full' indicates file reading operation with no destructive or modifying capability. Server context confirms it provides code intelligence and semantic search functionality.
Attacks that exploit this kind of access
read_file_full. It is categorised as a Read tool in the Portable MCP Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Portable MCP Toolkit MCP server in PolicyLayer and add a rule for read_file_full: 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 Portable MCP Toolkit. Nothing to install.
read_file_full 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_file_full 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_file_full. 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_file_full is provided by the Portable MCP Toolkit MCP server (mjdevaccount/aistack-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 →