Check if a pattern is compatible with current project dependencies.
AI agents call nyko_check to retrieve information from Nyko MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and inspects compatibility information against existing project dependencies. It performs a query or validation check with no ability to modify, delete, execute code, or commit financial transactions. The operation is informational and reversible by nature, making it a safe Read category with low severity.
From the tool's definition Tool description states 'Check if a pattern is compatible' — a read-only verification operation that queries project dependencies without modifying them. The verb 'check' indicates inspection/validation, not side effects.
Attacks that exploit this kind of access
Check if a pattern is compatible with current project dependencies. It is categorised as a Read tool in the Nyko MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Nyko MCP Server MCP server in PolicyLayer and add a rule for nyko_check: 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 Nyko MCP Server. Nothing to install.
nyko_check 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 nyko_check 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 nyko_check. 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.
nyko_check is provided by the Nyko MCP Server MCP server (nyko-ai/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 →