This record as markdown: /tools/soolaugust-0compactmem/unpin-memory.md
What unpin_memory does on 0CompactMem
AI agents use unpin_memory to create or update resources in 0CompactMem, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 0CompactMem environment.
Why unpin_memory is rated Medium
This tool modifies the pinned state of a memory chunk, making it eligible for eviction. It's a reversible state change (the chunk can be re-pinned), so it falls under Write rather than Destructive. However, misuse could lead to important memory being evicted and lost, giving it medium severity.
From the tool's definition 解除 chunk 在当前项目中的 pin,允许被自动淘汰 (Unpin a chunk in the current project, allowing it to be automatically evicted)
Attacks that exploit this kind of access
The rule that runs unpin_memory safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0CompactMem, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For unpin_memory, this is the rule to start with:
unpin_memory 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.
The button opens the PolicyLayer dashboard: create your workspace, connect 0CompactMem, apply this rule, and every unpin_memory call is checked against it from then on.
Questions about unpin_memory
解除 chunk 在当前项目中的 pin,允许被自动淘汰。. It is categorised as a Write tool in the 0CompactMem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 0CompactMem MCP server in PolicyLayer and add a rule for unpin_memory: 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 0CompactMem. Nothing to install.
unpin_memory 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 unpin_memory 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 unpin_memory. 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.
unpin_memory is provided by the 0CompactMem MCP server (soolaugust/0compactmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0CompactMem, and thousands of servers like it.
This server
Across the catalogue