Validates requirement statements against EARS notation patterns (ubiquitous, event-driven, state-driven, optional, unwanted, complex). Accepts a direct list of requirements OR reads from SPECIFICATION.md. Returns per-requirement compliance results with actionable suggestions.
AI agents call sdd_validate_ears to retrieve information from Specky without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs static analysis and validation of existing requirement statements against a notation schema. It inspects data, provides feedback, and returns results without modifying, executing code, destroying data, or creating side effects. This is a classic Read category tool—it queries/analyzes data structure and compliance without any irreversible or operational side effects.
From the tool's definition Tool description states it 'Validates requirement statements against EARS notation patterns' and 'Returns per-requirement compliance results with actionable suggestions.' The verb 'Validates' and 'Returns' indicate read-only inspection.
Documented attack patterns abuse exactly the kind of access sdd_validate_ears gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Specky, and nothing reaches the server without passing your rules. This is the rule we recommend for sdd_validate_ears:
{
"version": "1",
"default": "deny",
"tools": {
"sdd_validate_ears": {}
}
}sdd_validate_ears is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Validates requirement statements against EARS notation patterns (ubiquitous, event-driven, state-driven, optional, unwanted, complex). Accepts a direct list of requirements OR reads from SPECIFICATION.md. Returns per-requirement compliance results with actionable suggestions. It is categorised as a Read tool in the Specky MCP Server, which means it retrieves data without modifying state.
Register the Specky MCP server in PolicyLayer and add a rule for sdd_validate_ears: 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 Specky. Nothing to install.
sdd_validate_ears 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 sdd_validate_ears 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 sdd_validate_ears. 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.
sdd_validate_ears is provided by the Specky MCP server (paulasilvatech/specky). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Specky, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
56 Specky tools catalogued and risk-classified — across an index of 43,000+ MCP servers.