AI agents call dev_read to retrieve information from Jt 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 without modifying, executing, or deleting data. It is a passive read operation with no side effects, fitting the Read category. Severity is low because reading project files poses minimal risk even if misused by an AI agent—the data is already accessible within the project directory. Confidence is high due to explicit and unambiguous tool description.
From the tool's definition Tool name is 'dev_read' and description explicitly states 'Read the contents of a file within a project directory.' The verb 'read' and the absence of any modification, deletion, or execution capability clearly indicate this is a retrieval operation.
Attacks that exploit this kind of access
Read the contents of a file within a project directory. It is categorised as a Read tool in the Jt MCP Server, which means it retrieves data without modifying state.
Register the Jt MCP server in PolicyLayer and add a rule for dev_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 Jt. Nothing to install.
dev_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 dev_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 dev_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.
dev_read is provided by the Jt MCP server (@houkasaurusrex/jt-mcp-server). 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 →