AI agents call list_project_metrics to retrieve information from Mcp Wandb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves metric metadata from a Weights & Biases project. It performs a read-only operation that returns information about what metrics exist without creating, modifying, deleting, or executing any code. The blast radius is minimal — an agent cannot cause harm by listing metric names.
From the tool's definition Tool name 'list_project_metrics' and description states 'List all unique metric names logged in a W&B project' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all unique metric names logged in a W&B project. It is categorised as a Read tool in the Mcp Wandb MCP Server, which means it retrieves data without modifying state.
Register the Mcp Wandb MCP server in PolicyLayer and add a rule for list_project_metrics: 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 Mcp Wandb. Nothing to install.
list_project_metrics 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_project_metrics 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_project_metrics. 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_project_metrics is provided by the Mcp Wandb MCP server (tsilva/mcp-wandb). 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 →