terminal_read_file
AI agents call terminal_read_file to retrieve information from Global MCP Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves file contents without modifying data. However, severity is elevated to medium rather than low because: (1) the server operates across multiple sensitive contexts (local, SSH, GitHub), meaning accessed data could be highly confidential; (2) no description provided to confirm scope limitations; (3) potential for credential/secret exposure if files contain sensitive information.
From the tool's definition Tool name 'terminal_read_file' explicitly indicates file reading operation. Server description mentions 'comprehensive file operations' and 'local system, remote SSH servers, and GitHub repositories' access.
Attacks that exploit this kind of access
terminal_read_file. It is categorised as a Read tool in the Global MCP Manager MCP Server, which means it retrieves data without modifying state.
Register the Global MCP Manager MCP server in PolicyLayer and add a rule for terminal_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 Global MCP Manager. Nothing to install.
terminal_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 terminal_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 terminal_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.
terminal_read_file is provided by the Global MCP Manager MCP server (mamprimauto/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 →