AI agents use import_by_hashtag 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.
The tool imports external videos into the system, which is a create/write operation that modifies the agent's video collection reversibly. While it retrieves data from an external source, the primary effect is writing/storing that data locally.
From the tool's definition Tool name 'import_by_hashtag' and description 'Import videos from a social media platform by hashtag' indicate the tool creates new data records (imported videos) in the system's persistent memory.
Attacks that exploit this kind of access
Import videos from a social media platform by hashtag. 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 import_by_hashtag: 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.
import_by_hashtag 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 import_by_hashtag 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 import_by_hashtag. 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.
import_by_hashtag 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 →