AI agents call probe to retrieve information from Ffmpeg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The probe tool performs inspection and information retrieval of media file properties (format, streams, duration, codecs, resolution, bitrate). This is purely informational with no side effects, data modification, or external operations triggered. It matches the Read category definition of querying/retrieving data without side effects.
From the tool's definition Tool name 'probe' and description 'Get detailed media file information' indicate a read-only operation that retrieves and queries metadata about media files without modification.
Attacks that exploit this kind of access
Get detailed media file information (format, streams, duration, codecs, resolution, bitrate, etc.). It is categorised as a Read tool in the Ffmpeg MCP Server, which means it retrieves data without modifying state.
Register the Ffmpeg MCP server in PolicyLayer and add a rule for probe: 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 Ffmpeg. Nothing to install.
probe 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 probe 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 probe. 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.
probe is provided by the Ffmpeg MCP server (yuan66-hub/ffmpeg-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 →