List all .bb/.bbappend files under a Yocto layer path.
AI agents call scan_layer_recipe_files to retrieve information from Mcp Bitbake without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs file enumeration/discovery within a specified directory structure. It retrieves metadata about existing recipe files without modifying, executing, or deleting anything.
From the tool's definition Tool 'scan_layer_recipe_files' lists .bb/.bbappend files under a Yocto layer path. The verb 'list' and the read-only nature of directory scanning with no modification or execution indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all .bb/.bbappend files under a Yocto layer path. It is categorised as a Read tool in the Mcp Bitbake MCP Server, which means it retrieves data without modifying state.
Register the Mcp Bitbake MCP server in PolicyLayer and add a rule for scan_layer_recipe_files: 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 Mcp Bitbake. Nothing to install.
scan_layer_recipe_files 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 scan_layer_recipe_files 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 scan_layer_recipe_files. 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.
scan_layer_recipe_files is provided by the Mcp Bitbake MCP server (pkt-lab/mcp-bitbake). 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 →