query_wandb_gql_tool · Weights & Biases MCP Server MCP

WHAT IT DOES

What query_wandb_gql_tool does on Weights & Biases MCP Server

AI agents invoke query_wandb_gql_tool to trigger actions in Weights & Biases MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why query_wandb_gql_tool needs a policy

GraphQL endpoints can perform both queries (reads) and mutations (writes/destructive actions). With no description to constrain scope, and given the 'gql' suffix implying arbitrary GraphQL execution, this tool could run mutations that modify or delete W&B data. The most severe plausible category given the ambiguity is Execute. Confidence is reduced due to the empty description.

From the tool's definition Tool name: 'query_wandb_gql_tool' — the term 'gql' indicates GraphQL execution. Description is empty and uninformative, lowering confidence.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_wandb_gql_tool Rate-limited

query_wandb_gql_tool stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_wandb_gql_tool": {
      "limits": [
        {
          "counter": "query_wandb_gql_tool_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Weights & Biases MCP Server, so you can run agents against it safely.

FAQ

Questions about query_wandb_gql_tool

What does the query_wandb_gql_tool tool do? +

query_wandb_gql_tool. It is categorised as a Execute tool in the Weights & Biases MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_wandb_gql_tool? +

Register the Weights & Biases MCP Server MCP server in PolicyLayer and add a rule for query_wandb_gql_tool: 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 Weights & Biases MCP Server. Nothing to install.

What risk level is query_wandb_gql_tool? +

query_wandb_gql_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_wandb_gql_tool? +

Yes. Add a rate_limit block to the query_wandb_gql_tool 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.

How do I block query_wandb_gql_tool completely? +

Set action: deny in the PolicyLayer policy for query_wandb_gql_tool. 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.

What MCP server provides query_wandb_gql_tool? +

query_wandb_gql_tool is provided by the Weights & Biases MCP Server MCP server (riballes/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.