compact_session
AI agents call compact_session to retrieve information from Weighted Compact without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is part of a trio of explicitly read-only tools operating on a local memory substrate. No description is provided for the tool itself, lowering confidence slightly, but the server-level characterization as 'read-only' with 'zero outbound calls' and the sibling tools (search_pairs, substrate_info) being clearly informational in nature strongly indicate this retrieves or queries session data without side…
From the tool's definition Tool name 'compact_session' combined with server description stating 'Three read-only MCP tools' and 'Local-first inspectable memory substrate' indicates this is a read-only operation.
Attacks that exploit this kind of access
compact_session. It is categorised as a Read tool in the Weighted Compact MCP Server, which means it retrieves data without modifying state.
Register the Weighted Compact MCP server in PolicyLayer and add a rule for compact_session: 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 Weighted Compact. Nothing to install.
compact_session is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the compact_session 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_session. 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_session is provided by the Weighted Compact MCP server (zzallirog/weighted-compact). 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 →