AI agents use verify_memory 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.
This tool modifies the state of a memory entry, transitioning it from 'pending' to 'live'. This is a reversible write operation (the memory could potentially be archived or deleted later), not destructive. The blast radius is medium since promoting incorrect memories could pollute the context injected into future sessions, leading to bad coding decisions.
From the tool's definition Verify a pending auto-extracted memory — promotes it to live so it appears in recall results
Attacks that exploit this kind of access
Verify a pending auto-extracted memory — promotes it to live so it appears in recall results. 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 verify_memory: 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.
verify_memory 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 verify_memory 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 verify_memory. 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.
verify_memory 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 →