AI agents call list_channels to retrieve information from Mdfmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays metadata about channels in a measurement data file. It performs no write, delete, execute, or financial operations. The filtering capability is informational only. The blast radius of misuse is minimal — an AI agent cannot cause harm by listing channels. This is a straightforward Read operation.
From the tool's definition Tool name is 'list_channels' and description states 'List all channels in the MDF file with filtering' — a pure retrieval operation that queries available channels without modifying or executing anything.
Attacks that exploit this kind of access
List all channels in the MDF file with filtering. It is categorised as a Read tool in the Mdfmcp MCP Server, which means it retrieves data without modifying state.
Register the Mdf MCP server in PolicyLayer and add a rule for list_channels: 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 Mdfmcp. Nothing to install.
list_channels 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_channels 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_channels. 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_channels is provided by the Mdf MCP server (shanko-26/mdfmcp). 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 →