memory_timeline
AI agents call memory_timeline to retrieve information from Mono Memory MCP 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 timeline or historical memory data from the SQLite-backed persistent store. Without a description, confidence is moderate, but the naming convention ('timeline' suggests chronological retrieval) and position among read-like siblings (get, search, context) strongly suggests a Read operation with no side effects.
From the tool's definition Tool name 'memory_timeline' and server context indicate querying/retrieving temporal memory records. No description provided, but naming pattern matches other sibling 'memory_*' tools (memory_get, memory_search) which are read operations.
Attacks that exploit this kind of access
memory_timeline. It is categorised as a Read tool in the Mono Memory MCP MCP Server, which means it retrieves data without modifying state.
Register the Mono Memory MCP server in PolicyLayer and add a rule for memory_timeline: 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 Mono Memory MCP. Nothing to install.
memory_timeline 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_timeline 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_timeline. 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_timeline is provided by the Mono Memory MCP server (potato-castle/mono-memory-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 →