Refresh the local Temporal documentation corpus by syncing with the latest docs.
AI agents use docs.refresh to create or update resources in Temporal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Temporal environment.
This tool modifies the local documentation corpus by syncing/updating it with new content. It is a write operation (updating stored data) rather than a pure read. While it doesn't delete data irreversibly, it overwrites the existing corpus with new content. Misuse could corrupt the documentation corpus used by the AI agent for guidance, potentially leading to incorrect Temporal code generation.
From the tool's definition Refresh the local Temporal documentation corpus by syncing with the latest docs.
Documented attack patterns abuse exactly the kind of access docs.refresh gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Temporal, and nothing reaches the server without passing your rules. This is the rule we recommend for docs.refresh:
{
"version": "1",
"default": "deny",
"tools": {
"docs.refresh": {
"limits": [
{
"counter": "docs.refresh_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}docs.refresh 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.
Refresh the local Temporal documentation corpus by syncing with the latest docs. It is categorised as a Write tool in the Temporal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Temporal MCP server in PolicyLayer and add a rule for docs.refresh: 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 Temporal. Nothing to install.
docs.refresh 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 docs.refresh 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 docs.refresh. 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.
docs.refresh is provided by the Temporal MCP server (stevekinney/temporal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Temporal, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
28 Temporal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.