Context for creating video applications using VideoDB
AI agents call doc_assistant to retrieve information from VideoDB Director without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool description suggests it provides contextual information or documentation to assist in building video applications. This is a read/query operation with no apparent side effects. Severity is low because misuse would at most expose documentation content. Confidence is moderate because the description is vague and doesn't explicitly describe what actions are taken.
From the tool's definition 'Context for creating video applications using VideoDB' — provides context/documentation, implying retrieval of informational content
Documented attack patterns abuse exactly the kind of access doc_assistant gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VideoDB Director, and nothing reaches the server without passing your rules. This is the rule we recommend for doc_assistant:
{
"version": "1",
"default": "deny",
"tools": {
"doc_assistant": {}
}
}doc_assistant 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.
Context for creating video applications using VideoDB. It is categorised as a Read tool in the VideoDB Director MCP Server, which means it retrieves data without modifying state.
Register the VideoDB Director MCP server in PolicyLayer and add a rule for doc_assistant: 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 VideoDB Director. Nothing to install.
doc_assistant 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 doc_assistant 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 doc_assistant. 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.
doc_assistant is provided by the VideoDB Director MCP server (video-db/agent-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 VideoDB Director tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 VideoDB Director tools catalogued and risk-classified — across an index of 42,500+ MCP servers.