Retrieves all applications from the Plan system
AI agents call get_applications to retrieve information from MCP DevOps Plan Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and returns application data without creating, modifying, deleting, or executing any operations. The verb 'retrieves' and lack of any state-changing capability places it firmly in the Read category with low severity since it only exposes existing data.
From the tool's definition Tool name is 'get_applications' and description states it 'Retrieves all applications from the Plan system' - a straightforward data retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Retrieves all applications from the Plan system. It is categorised as a Read tool in the MCP DevOps Plan Server MCP Server, which means it retrieves data without modifying state.
Register the MCP DevOps Plan Server MCP server in PolicyLayer and add a rule for get_applications: 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 DevOps Plan Server. Nothing to install.
get_applications 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_applications 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_applications. 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_applications is provided by the MCP DevOps Plan Server MCP server (mrchris2000/mcp-devops-plan). 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 →