AI agents call filter_memos to retrieve information from Memos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool filters memos using a CEL (Common Expression Language) expression, which is a read/query operation. It retrieves a subset of memos based on filter criteria without modifying any data. The description translates to 'Filter memos using CEL expressions', indicating a pure read operation with no side effects.
From the tool's definition 过滤备忘录 (filter memos) - the tool filters/queries memos using a CEL expression
Attacks that exploit this kind of access
使用 CEL 表达式过滤备忘录. It is categorised as a Read tool in the Memos MCP Server, which means it retrieves data without modifying state.
Register the Memos MCP server in PolicyLayer and add a rule for filter_memos: 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 Memos. Nothing to install.
filter_memos 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 filter_memos 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 filter_memos. 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.
filter_memos is provided by the Memos MCP server (yuzhi-jiang/memos-mcp). 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 →