Сверка «числовых» имён точек: есть в выгрузках, но нет в мастере (и наоборот).
AI agents call reconcile_by_name to retrieve information from Navisworks Viewpoints without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to perform a read-only audit or comparison operation - it identifies discrepancies between viewpoint sets without the description indicating any modification, deletion, or execution of external operations. It fits the Read category as a retrieval/query function that reports differences.
From the tool's definition Tool description indicates it performs reconciliation/verification (сверка) of 'numeric' names between viewpoints - checking what exists in exports but not in master and vice versa.
Attacks that exploit this kind of access
Сверка «числовых» имён точек: есть в выгрузках, но нет в мастере (и наоборот). It is categorised as a Read tool in the Navisworks Viewpoints MCP Server, which means it retrieves data without modifying state.
Register the Navisworks Viewpoints MCP server in PolicyLayer and add a rule for reconcile_by_name: 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 Navisworks Viewpoints. Nothing to install.
reconcile_by_name 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 reconcile_by_name 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 reconcile_by_name. 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.
reconcile_by_name is provided by the Navisworks Viewpoints MCP server (mikhalchankasm/navisworks-viewpoints-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 →