Read-only discovery: dumps a clip
AI agents call probe_effects to retrieve information from Media-Editor-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is explicitly described as 'read-only' and performs discovery/inspection of clip effects. It retrieves information about a clip without creating, modifying, deleting, or executing any operations. This is a classic Read category tool with minimal security risk—an AI agent cannot misuse it to cause damage since it only queries data.
From the tool's definition Tool name 'probe_effects' combined with description 'Read-only discovery: dumps a clip' indicates a query/inspection operation with no modification or side effects.
Attacks that exploit this kind of access
Read-only discovery: dumps a clip. It is categorised as a Read tool in the Media-Editor-MCP MCP Server, which means it retrieves data without modifying state.
Register the Media-Editor- MCP server in PolicyLayer and add a rule for probe_effects: 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 Media-Editor-MCP. Nothing to install.
probe_effects 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_effects 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_effects. 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_effects is provided by the Media-Editor- MCP server (nguyenph88/media-editor-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 →