Write a compact caller-provided checkpoint summary for a non-terminal TaskRun and return the checkpoint metadata.
AI agents use oc_task_run_checkpoint to create or update resources in OpenChrome — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenChrome environment.
This tool writes/saves a checkpoint summary for a running task. It creates or modifies checkpoint state data, which is reversible and scoped to task tracking metadata. No code execution, deletion, or financial operations are involved.
From the tool's definition 'Write a compact caller-provided checkpoint summary for a non-terminal TaskRun and return the checkpoint metadata'
Documented attack patterns abuse exactly the kind of access oc_task_run_checkpoint gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenChrome, and nothing reaches the server without passing your rules. This is the rule we recommend for oc_task_run_checkpoint:
{
"version": "1",
"default": "deny",
"tools": {
"oc_task_run_checkpoint": {
"limits": [
{
"counter": "oc_task_run_checkpoint_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}oc_task_run_checkpoint 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.
Write a compact caller-provided checkpoint summary for a non-terminal TaskRun and return the checkpoint metadata. It is categorised as a Write tool in the OpenChrome MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenChrome MCP server in PolicyLayer and add a rule for oc_task_run_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 OpenChrome. Nothing to install.
oc_task_run_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 oc_task_run_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 oc_task_run_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.
oc_task_run_checkpoint is provided by the OpenChrome MCP server (shaun0927/openchrome). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 106 OpenChrome tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
106 OpenChrome tools catalogued and risk-classified — across an index of 42,500+ MCP servers.