List deployments with optional filtering
AI agents call list_deployments to retrieve information from Mender MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves deployment information without side effects. It queries existing data and applies filters, which is a classic Read operation. The explicit 'read-only access' claim in the server description, combined with the tool's query semantics, confirms no risk of data modification, execution, or financial impact.
From the tool's definition Tool name 'list_deployments' and description 'List deployments with optional filtering' indicate a query/retrieval operation. Server description explicitly states 'read-only access' and 'deployment monitoring'.
Attacks that exploit this kind of access
List deployments with optional filtering. It is categorised as a Read tool in the Mender MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mender MCP Server MCP server in PolicyLayer and add a rule for list_deployments: 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 Mender MCP Server. Nothing to install.
list_deployments 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 list_deployments 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 list_deployments. 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.
list_deployments is provided by the Mender MCP Server MCP server (pasinskim/mender-mcp). 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 →