AI agents call list_audio_inputs to retrieve information from Obs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and enumerates existing audio input configuration—no side effects, reversible modifications, code execution, data destruction, or financial impact. The blast radius of misuse is minimal; an attacker gains only information about what audio inputs are available on the system.
From the tool's definition Tool name 'list_audio_inputs' and description 'List all audio input sources' indicate a read-only query operation that retrieves data about available audio devices without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List all audio input sources (mics, desktop audio, etc.). It is categorised as a Read tool in the Obs MCP Server, which means it retrieves data without modifying state.
Register the Obs MCP server in PolicyLayer and add a rule for list_audio_inputs: 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 Obs. Nothing to install.
list_audio_inputs 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 list_audio_inputs 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 list_audio_inputs. 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.
list_audio_inputs is provided by the Obs MCP server (larscangit/obs-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 →