記録のソース確認（会話ログ参照）
AI agents call memory_open_source 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.
The tool appears to retrieve or view the source/origin of records by referencing conversation logs. This is a read-only operation with no apparent side effects. Confidence is moderate because the description is brief and in Japanese, leaving some ambiguity about whether it might trigger any write operations, but the phrasing 'confirmation' and 'reference' strongly suggest a read-only action.
From the tool's definition 記録のソース確認（会話ログ参照）— translates to 'source confirmation of records (conversation log reference)'
Attacks that exploit this kind of access
記録のソース確認（会話ログ参照）. 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_open_source: 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_open_source 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_open_source 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_open_source. 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_open_source 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 →