AI agents use openspec_reject_change to create or update resources in OpenSpec MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenSpec MCP environment.
Rejecting a change modifies its state/metadata reversibly—the change record remains intact and could theoretically be resubmitted or re-reviewed. This is not destructive deletion (no purge), not financial, and not arbitrary code execution. It falls under Write (modifies data reversibly) rather than Execute because it targets a specific state change in a workflow system, not arbitrary operations.
From the tool's definition Tool name 'openspec_reject_change' and description 'Reject a change' indicate modification of change proposal status/state. This is a write operation that updates an existing change record's approval status to a rejected state.
Documented attack patterns abuse exactly the kind of access openspec_reject_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_reject_change:
{
"version": "1",
"default": "deny",
"tools": {
"openspec_reject_change": {
"limits": [
{
"counter": "openspec_reject_change_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}openspec_reject_change stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Reject a change. It is categorised as a Write tool in the OpenSpec MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenSpec MCP server in PolicyLayer and add a rule for openspec_reject_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_reject_change is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the openspec_reject_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_reject_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_reject_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.