Validate NM3 XML for compliance with spec
AI agents call validate_nm3 to retrieve information from Markdown3D MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Validation is a read-only operation that analyzes input (NM3 XML) against a specification and reports results, with no side effects, data modification, deletion, or external command execution. This is consistent with the Read category pattern of query/inspection operations.
From the tool's definition Tool name 'validate_nm3' with description 'Validate NM3 XML for compliance with spec' indicates a validation/inspection operation that checks conformance without modifying data.
Attacks that exploit this kind of access
Validate NM3 XML for compliance with spec. It is categorised as a Read tool in the Markdown3D MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Markdown3D MCP Server MCP server in PolicyLayer and add a rule for validate_nm3: 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 Markdown3D MCP Server. Nothing to install.
validate_nm3 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 validate_nm3 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_nm3. 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_nm3 is provided by the Markdown3D MCP Server MCP server (mushroomfleet/markdown3d-mcp). 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 →