Create a new Claude Code session
AI agents invoke create_session to trigger actions in Shannon MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Creating a Claude Code session initiates an external process capable of executing code, running shell commands, and performing arbitrary operations depending on the session's subsequent instructions. While session creation itself may not immediately execute code, it establishes an execution context with potentially broad capabilities.
From the tool's definition "Create a new Claude Code session" — spawns a new Claude Code CLI process/session, which triggers external operations and establishes a running agent environment.
Attacks that exploit this kind of access
Create a new Claude Code session. It is categorised as a Execute tool in the Shannon MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Shannon MCP server in PolicyLayer and add a rule for create_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 Shannon MCP. Nothing to install.
create_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_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_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_session is provided by the Shannon MCP server (krzemienski/shannon-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 →