Refresh and compact memory indexes. Falls back to a safe refresh if the compactor is not available.
AI agents use compact_memories to create or update resources in Reporecall — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Reporecall environment.
This tool modifies/reorganizes internal memory indexes by compacting and refreshing them. It writes/rewrites index data but doesn't appear to permanently delete content (it 'compacts' which typically reorganizes rather than destroys). The blast radius is medium since misuse could corrupt or reorganize memory indexes used for codebase intelligence.
From the tool's definition Refresh and compact memory indexes. Falls back to a safe refresh if the compactor is not available.
Documented attack patterns abuse exactly the kind of access compact_memories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Reporecall, and nothing reaches the server without passing your rules. This is the rule we recommend for compact_memories:
{
"version": "1",
"default": "deny",
"tools": {
"compact_memories": {
"limits": [
{
"counter": "compact_memories_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}compact_memories 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 and compact memory indexes. Falls back to a safe refresh if the compactor is not available. It is categorised as a Write tool in the Reporecall MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Reporecall MCP server in PolicyLayer and add a rule for compact_memories: 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 Reporecall. Nothing to install.
compact_memories 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 compact_memories 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 compact_memories. 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.
compact_memories is provided by the Reporecall MCP server (proofofwork-agency/reporecall). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 Reporecall tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 Reporecall tools catalogued and risk-classified — across an index of 42,500+ MCP servers.