AI agents call list_wandb_runs 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 experiment run information from Weights & Biases. It performs no modifications, deletions, or state changes—it simply lists existing data. This is a straightforward Read operation with minimal security risk, as the worst-case scenario is unauthorized visibility into project metadata.
From the tool's definition Tool name 'list_wandb_runs' and description 'List all runs for a given W&B project' indicate a read-only query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
List all runs for a given 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_wandb_runs: 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_wandb_runs 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_wandb_runs 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_wandb_runs. 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_wandb_runs 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 →