Get package manifest (package.xml) as a structured dictionary
AI agents call get_package_manifest to retrieve information from ROS 2 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation to introspect ROS 2 package metadata. It has no side effects, does not execute code or services, and cannot modify system state. The risk is minimal as it only exposes static package configuration information already present in the ROS 2 environment.
From the tool's definition Tool retrieves and returns package manifest data (package.xml) as a structured dictionary. The name and description both indicate a query/fetch operation with no modification or execution of ROS 2 systems.
Attacks that exploit this kind of access
Get package manifest (package.xml) as a structured dictionary. It is categorised as a Read tool in the ROS 2 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ROS 2 MCP Server MCP server in PolicyLayer and add a rule for get_package_manifest: 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 ROS 2 MCP Server. Nothing to install.
get_package_manifest 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 get_package_manifest 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 get_package_manifest. 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.
get_package_manifest is provided by the ROS 2 MCP Server MCP server (ranch-hand-robotics/rde-mcp-ros-2). 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 →