AI agents use observe to create or update resources in Tages — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tages environment.
The tool accepts freeform observations and writes extracted memory entries to a persistent cross-session store. This is a Write operation because it creates/modifies stored data (memories) in a reversible way. Severity is medium because an AI agent could inadvertently store incorrect architectural decisions or misleading context that persists across sessions, polluting future sessions' understanding of the codebase.
From the tool's definition 'Tages silently extracts memories from your observations' — the tool writes/stores memory data extracted from natural language observations into persistent SQLite storage
Attacks that exploit this kind of access
Report what you are doing or learning — Tages silently extracts memories from your observations. Call this naturally as you work, no need to format. It is categorised as a Write tool in the Tages MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tages MCP server in PolicyLayer and add a rule for observe: 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 Tages. Nothing to install.
observe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the observe 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 observe. 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.
observe is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →