Start a new budget-enforced session. Call once at the start of every task before any other work. Returns session_id in the response — store it and pass it to all subsequent l6e calls. Do NOT pass session_id or task_description — use task_summary for a brief task label.
AI agents invoke l6e_run_start to trigger actions in L6e. 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.
l6e_run_start triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Start a new budget-enforced session. Call once at the start of every task before any other work. Returns session_id in the response — store it and pass it to all subsequent l6e calls. Do NOT pass session_id or task_description — use task_summary for a brief task label. It is categorised as a Execute tool in the L6e MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the L6e MCP server in PolicyLayer and add a rule for l6e_run_start: 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 L6e. Nothing to install.
l6e_run_start 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 l6e_run_start 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 l6e_run_start. 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.
l6e_run_start is provided by the L6e MCP server (l6e-ai/l6e-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 →