AI agents use add_memory to create or update resources in Videoseek — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Videoseek environment.
This tool creates and persists new data (memories) with semantic indexing, making it a Write category action. Severity is medium because an AI agent could store malicious, false, or private information in the system, but the impact is limited to data modification rather than deletion or code execution.
From the tool's definition Tool description states 'Store a text memory with semantic indexing' — this is a create/write operation that persists data. The word 'Store' indicates data is being written to a system.
Attacks that exploit this kind of access
Store a text memory with semantic indexing. Memories are searchable. It is categorised as a Write tool in the Videoseek MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Videoseek MCP server in PolicyLayer and add a rule for add_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 Videoseek. Nothing to install.
add_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 add_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 add_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.
add_memory is provided by the Videoseek MCP server (kennyzheng-builds/videoseek-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 →