Validate Python visualization code — run before show().
AI agents invoke validate to trigger actions in HoloViz 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.
Despite being framed as a validation step, this tool runs Python visualization code in an execution environment. Executing arbitrary Python code can have side effects beyond mere data retrieval, including file system access, network calls, or other operations depending on the code provided.
From the tool's definition 'Validate Python visualization code — run before show()' — the tool executes Python code to perform validation
Attacks that exploit this kind of access
Validate Python visualization code — run before show(). It is categorised as a Execute tool in the HoloViz MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the HoloViz MCP Server MCP server in PolicyLayer and add a rule for validate: 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 HoloViz MCP Server. Nothing to install.
validate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the validate 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 validate. 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.
validate is provided by the HoloViz MCP Server MCP server (sumayabee/holoviz-mcp-server). 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 →