create_kasm_session
AI agents use create_kasm_session to create or update resources in Kasm MCP Server v2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kasm MCP Server v2 environment.
The tool name 'create_kasm_session' strongly implies creating a new containerized desktop session. This is a Write operation (creates a new resource). The description is empty, which lowers confidence slightly. Severity is medium because creating sessions consumes resources and could be misused to spin up many containers, but it is reversible (sessions can be destroyed).
From the tool's definition Tool name: create_kasm_session; description is empty. Inferred from name and server context (session management in Kasm Workspaces).
Attacks that exploit this kind of access
create_kasm_session. It is categorised as a Write tool in the Kasm MCP Server v2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kasm MCP Server v2 MCP server in PolicyLayer and add a rule for create_kasm_session: 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 Kasm MCP Server v2. Nothing to install.
create_kasm_session is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_kasm_session 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 create_kasm_session. 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.
create_kasm_session is provided by the Kasm MCP Server v2 MCP server (roguedev-ai/kasm-mcp-server-v2). 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 →