Get or manage the working memory buffer - the active context window for the current session.
AI agents call memory_working to retrieve information from MCP Router without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The primary function described is 'Get or manage' the working memory buffer. 'Get' is a read operation. 'Manage' is ambiguous and could imply write operations, but in context of a working memory/active context window, this is most likely a read-oriented retrieval of the current session's context. Given the ambiguity of 'manage', confidence is moderate.
From the tool's definition 'Get or manage the working memory buffer - the active context window for the current session'
Attacks that exploit this kind of access
Get or manage the working memory buffer - the active context window for the current session. It is categorised as a Read tool in the MCP Router MCP Server, which means it retrieves data without modifying state.
Register the MCP Router MCP server in PolicyLayer and add a rule for memory_working: 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 Router. Nothing to install.
memory_working 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 memory_working 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 memory_working. 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.
memory_working is provided by the MCP Router MCP server (justinpreston/mcp-router). 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 →