Archive old/inactive conversations to free up space. Moves conversations that haven
AI agents use archive_conversations to create or update resources in Claude Code Toolkit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Code Toolkit environment.
Archiving is a Write operation—it modifies the state of conversations by moving them to archived storage, but the action is reversible (conversations can typically be unarchived). This is not Destructive because the data is preserved, not deleted. While it affects data organization, it doesn't trigger external operations (Execute) or cause financial impact (Financial).
From the tool's definition Tool description states "Archive old/inactive conversations to free up space. Moves conversations that..." The key action is 'Moves', which is a reversible modification of data (changing conversation location/status to archived state).
Documented attack patterns abuse exactly the kind of access archive_conversations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for archive_conversations:
{
"version": "1",
"default": "deny",
"tools": {
"archive_conversations": {
"limits": [
{
"counter": "archive_conversations_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}archive_conversations 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.
Archive old/inactive conversations to free up space. Moves conversations that haven. It is categorised as a Write tool in the Claude Code Toolkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Code Toolkit MCP server in PolicyLayer and add a rule for archive_conversations: 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 Claude Code Toolkit. Nothing to install.
archive_conversations 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 archive_conversations 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 archive_conversations. 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.
archive_conversations is provided by the Claude Code Toolkit MCP server (asifkibria/claude-code-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code Toolkit, 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.
40 Claude Code Toolkit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.