AI agents use openspec_add_review 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.
This tool creates new review comments, which are reversible modifications to a change or spec entity. It does not execute code, delete data, or move money. The medium severity reflects that malicious review comments could mislead approval workflows or create reputational harm, but the impact is limited to comment data rather than core specifications or financial systems.
From the tool's definition Tool name 'openspec_add_review' and description 'Add a review comment to a change or spec' indicate the tool creates or appends review data to existing change or spec records. The verb 'add' is a modification action.
Documented attack patterns abuse exactly the kind of access openspec_add_review 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_add_review:
{
"version": "1",
"default": "deny",
"tools": {
"openspec_add_review": {
"limits": [
{
"counter": "openspec_add_review_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}openspec_add_review 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.
Add a review comment to a change or spec. 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_add_review: 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_add_review 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_add_review 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_add_review. 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_add_review 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.