pin_memory
AI agents use pin_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.
The tool name 'pin_memory' strongly suggests it pins memory entries (likely setting mlock/pinned flags on records in the SQLite store) to prevent eviction. This is a Write-category operation — it modifies the state of existing memory records reversibly (the sibling tool 'unpin_memory' confirms it is reversible).
From the tool's definition Tool name 'pin_memory'; server description mentions 'mlock pinning' as a memory management primitive alongside 'demand paging' and 'kswapd eviction'
Attacks that exploit this kind of access
pin_memory. 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 pin_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.
pin_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 pin_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 pin_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.
pin_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →