AI agents call openspec_validate_change to retrieve information from OpenSpec MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Validation is an introspective operation—it queries and checks the change proposal against defined rules or schema, returning assessment results but not modifying, deleting, or executing external operations. This falls squarely in the Read category. Severity is low because validation poses minimal risk; at worst it could return information about a proposal, but cannot alter data or trigger external systems.
From the tool's definition Tool name 'openspec_validate_change' and description 'Validate a change proposal' indicate a validation/checking operation that examines a proposal without modifying it. Validation is a read-only operation that assesses state without side effects.
Documented attack patterns abuse exactly the kind of access openspec_validate_change gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenSpec MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for openspec_validate_change:
{
"version": "1",
"default": "deny",
"tools": {
"openspec_validate_change": {}
}
}openspec_validate_change 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.
Validate a change proposal. It is categorised as a Read tool in the OpenSpec MCP MCP Server, which means it retrieves data without modifying state.
Register the OpenSpec MCP server in PolicyLayer and add a rule for openspec_validate_change: 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 OpenSpec MCP. Nothing to install.
openspec_validate_change 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 openspec_validate_change 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 openspec_validate_change. 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.
openspec_validate_change is provided by the OpenSpec MCP server (lumiaqian/openspec-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenSpec MCP, 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.
40 OpenSpec MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.