AI agents call read_bp_program to retrieve information from UOFastMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns program source code without executing it, modifying it, or causing side effects. It is a pure read operation analogous to viewing a file. The low severity reflects that reading source code poses minimal risk unless it exposes highly sensitive proprietary logic, but that is a data classification concern rather than a functional capability risk.
From the tool's definition Tool name 'read_bp_program' and description 'Read source code from a UniData BP (Basic Program) file. Returns the program source as text.' indicate retrieval of existing program source without modification.
Attacks that exploit this kind of access
Read source code from a UniData BP (Basic Program) file. Returns the program source as text. It is categorised as a Read tool in the UOFastMCP MCP Server, which means it retrieves data without modifying state.
Register the UOFast MCP server in PolicyLayer and add a rule for read_bp_program: 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 UOFastMCP. Nothing to install.
read_bp_program 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_bp_program 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_bp_program. 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_bp_program is provided by the UOFast MCP server (rokipark/uofastmcp). 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 →