最近の文脈取得（新チャット開始時に使用）
AI agents call memory_get_recent_context to retrieve information from MCP Memory System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored contextual information without modifying, deleting, or executing operations. It enables context continuity by fetching previously stored decisions and settings. No side effects or irreversible actions are possible. Severity is low because misuse would only expose historical context data rather than cause operational harm.
From the tool's definition Tool description indicates retrieval of recent context ('最近の文脈取得' = 'retrieve recent context'). Named 'memory_get_recent_context' with 'get' indicating data retrieval.
Attacks that exploit this kind of access
最近の文脈取得（新チャット開始時に使用）. It is categorised as a Read tool in the MCP Memory System MCP Server, which means it retrieves data without modifying state.
Register the MCP Memory System MCP server in PolicyLayer and add a rule for memory_get_recent_context: 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 Memory System. Nothing to install.
memory_get_recent_context 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_get_recent_context 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_get_recent_context. 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_get_recent_context is provided by the MCP Memory System MCP server (workerportfolio/mcp-memory-system). 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 →