Accepts or rejects a proposed governance scope amendment. Precondition: the amendment must exist and be in a reviewable state — use get_scope_amendments to find amendment IDs. status must be
AI agents use review_amendment to create or update resources in Engrams — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engrams environment.
The tool updates the status of a governance amendment (approve or reject), which is a write operation changing the state of a record. It does not delete data, execute code, or involve financial transactions. The severity is medium because approving/rejecting governance rules can affect project-wide compliance and behavior, but the action itself is a state transition that could potentially be revisited.
From the tool's definition 'Accepts or rejects a proposed governance scope amendment' — this modifies the state of an amendment record (approval/rejection), which is a reversible state change on existing data.
Documented attack patterns abuse exactly the kind of access review_amendment gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engrams, and nothing reaches the server without passing your rules. This is the rule we recommend for review_amendment:
{
"version": "1",
"default": "deny",
"tools": {
"review_amendment": {
"limits": [
{
"counter": "review_amendment_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}review_amendment 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.
Accepts or rejects a proposed governance scope amendment. Precondition: the amendment must exist and be in a reviewable state — use get_scope_amendments to find amendment IDs. status must be. It is categorised as a Write tool in the Engrams MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Engrams MCP server in PolicyLayer and add a rule for review_amendment: 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 Engrams. Nothing to install.
review_amendment 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 review_amendment 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 review_amendment. 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.
review_amendment is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engrams, 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.
42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.