Decode Nova Poshta API message code into human readable text. Doc 1.2 explains how every response contains success/data/errors/warnings/info blocks with numeric codes; this helper calls getMessageCodeText to map those codes to UA/RU descriptions.
AI agents call reference_decode_message to retrieve information from Novaposhta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only utility that retrieves and translates error/info codes from the Nova Poshta API documentation into human-readable format. It performs a straightforward reference lookup without creating, modifying, deleting, or executing any operations. The tool has minimal security risk as it only reads static code-to-text mappings.
From the tool's definition Tool description states it 'Decode[s] Nova Poshta API message code into human readable text' and 'map[s] those codes to UA/RU descriptions' — purely a lookup/translation operation with no side effects.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Decode Nova Poshta API message code into human readable text. Doc 1.2 explains how every response contains success/data/errors/warnings/info blocks with numeric codes; this helper calls getMessageCodeText to map those codes to UA/RU descriptions. It is categorised as a Read tool in the Novaposhta MCP Server, which means it retrieves data without modifying state.
Register the Novaposhta MCP server in PolicyLayer and add a rule for reference_decode_message: 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 Novaposhta. Nothing to install.
reference_decode_message 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 reference_decode_message 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 reference_decode_message. 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.
reference_decode_message is provided by the Novaposhta MCP server (@shopana/novaposhta-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 →