AI agents use linear_completeCycle to create or update resources in Linear — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Linear environment.
This tool updates the status of a project cycle from active to complete, which is a reversible Write operation. It does not delete data (Destructive), execute arbitrary code (Execute), or involve financial transactions (Financial). The blast radius is medium because marking cycles complete could affect team planning and visibility, potentially hiding active work, but the operation is recoverable.
From the tool's definition Tool name 'linear_completeCycle' and description 'Mark a cycle as complete' indicate a state change operation on a cycle entity in Linear. This modifies existing data (cycle status) but is reversible—the cycle can be reopened or its status changed again.
Documented attack patterns abuse exactly the kind of access linear_completeCycle gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Linear, and nothing reaches the server without passing your rules. This is the rule we recommend for linear_completeCycle:
{
"version": "1",
"default": "deny",
"tools": {
"linear_completeCycle": {
"limits": [
{
"counter": "linear_completecycle_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}linear_completeCycle stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Mark a cycle as complete. It is categorised as a Write tool in the Linear MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Linear MCP server in PolicyLayer and add a rule for linear_completeCycle: 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 Linear. Nothing to install.
linear_completeCycle 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 linear_completeCycle 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 linear_completeCycle. 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.
linear_completeCycle is provided by the Linear MCP server (tacticlaunch/mcp-linear). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 182 Linear tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
182 Linear tools catalogued and risk-classified — across an index of 42,500+ MCP servers.