Update a shared memory item. Only editable items or owned items can be updated.
AI agents use shared-memory-update to create or update resources in MCP LLM Generator v2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP LLM Generator v2 environment.
This tool creates or modifies data in a shared memory system. While the operation is reversible (typical of Write category), the potential blast radius is medium because: (1) updates could affect shared context used by multiple agents or users, (2) malicious updates could corrupt conversation history or context that other components depend on, and (3) the shared nature means impact extends beyond a single operation.
From the tool's definition The tool name 'shared-memory-update' and description 'Update a shared memory item' indicate a write operation that modifies data. The permission model ('Only editable items or owned items can be updated') suggests reversible updates with access controls.
Attacks that exploit this kind of access
Update a shared memory item. Only editable items or owned items can be updated. It is categorised as a Write tool in the MCP LLM Generator v2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP LLM Generator v2 MCP server in PolicyLayer and add a rule for shared-memory-update: 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 MCP LLM Generator v2. Nothing to install.
shared-memory-update 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 shared-memory-update 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 shared-memory-update. 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.
shared-memory-update is provided by the MCP LLM Generator v2 MCP server (mako10k/mcp-llm-generator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
shared-memory-update is one line of MCP LLM Generator v2's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →