AI agents call fetch_recorded_image to retrieve information from MCP Server - VMS Integration without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches pre-recorded image/video data from a CCTV system without modifying, deleting, or executing code. It is a passive data retrieval operation with no side effects. The empty description lowers confidence slightly, but the naming convention and server context strongly indicate a Read operation.
From the tool's definition Tool name 'fetch_recorded_image' and server description context indicating retrieval of 'recorded video streams' and 'playback dialogs for specific channels and timestamps'.
Documented attack patterns abuse exactly the kind of access fetch_recorded_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server - VMS Integration, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_recorded_image:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_recorded_image": {}
}
}fetch_recorded_image is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
fetch_recorded_image. It is categorised as a Read tool in the MCP Server - VMS Integration MCP Server, which means it retrieves data without modifying state.
Register the MCP Server - VMS Integration MCP server in PolicyLayer and add a rule for fetch_recorded_image: 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 MCP Server - VMS Integration. Nothing to install.
fetch_recorded_image is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fetch_recorded_image 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 fetch_recorded_image. 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.
fetch_recorded_image is provided by the MCP Server - VMS Integration MCP server (jyjune/mcp_vms). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Server - VMS Integration, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 MCP Server - VMS Integration tools catalogued and risk-classified — across an index of 43,000+ MCP servers.