This record as markdown: /tools/0xchamin-mcptube/save-tags.md
What save_tags does on Mcptube Vision
AI agents use save_tags to create or update resources in Mcptube Vision, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcptube Vision environment.
Why save_tags is rated Medium
This tool creates or modifies tag data associated with videos, which is a Write operation. It does not delete data (not Destructive), does not execute external code or commands (not Execute), does not move money (not Financial), and has side effects beyond just reading (not Read).
From the tool's definition The tool name 'save_tags' and description 'Save classification tags for a video' indicate it modifies metadata associated with a video by writing tags to the knowledge base. This is a reversible write operation on structured data (tags/classifications).
Attacks that exploit this kind of access
The rule that runs save_tags safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcptube Vision, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For save_tags, this is the rule to start with:
save_tags stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcptube Vision, apply this rule, and every save_tags call is checked against it from then on.
Questions about save_tags
Save classification tags for a video. It is categorised as a Write tool in the Mcptube Vision MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcptube Vision MCP server in PolicyLayer and add a rule for save_tags: 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 Mcptube Vision. Nothing to install.
save_tags 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 save_tags 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 save_tags. 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.
save_tags is provided by the Mcptube Vision MCP server (0xchamin/mcptube). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcptube Vision, and thousands of servers like it.
This server
Across the catalogue