AI agents use task_checkpoint to create or update resources in AgentOS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AgentOS environment.
This tool writes data to persistent storage (checkpoint state) without deleting or overwriting existing data irreversibly. While it modifies state, the operation is reversible—new checkpoints can overwrite old ones, and the original task continues.
From the tool's definition Tool name 'task_checkpoint' and description 'Save a checkpoint for an active task to preserve current state' indicate the tool creates or modifies state data (checkpoint records) for task resumption or recovery.
Attacks that exploit this kind of access
Save a checkpoint for an active task to preserve current state. It is categorised as a Write tool in the AgentOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AgentOS MCP server in PolicyLayer and add a rule for task_checkpoint: 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 AgentOS. Nothing to install.
task_checkpoint 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 task_checkpoint 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 task_checkpoint. 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.
task_checkpoint is provided by the AgentOS MCP server (netflypsb/agentos). 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 →