AI agents use hasura-mutations to create or update resources in SettleMint — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SettleMint environment.
GraphQL mutations are write operations by definition, covering create/update/delete. However, since mutations can include destructive operations (delete), severity is elevated. Confidence is reduced due to the empty description. Sibling tool 'hasura-mutation' (singular) likely performs the same function; the plural form may batch multiple mutations.
From the tool's definition Tool name contains 'mutations', which in GraphQL terminology refers to operations that create, update, or delete data. The description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access hasura-mutations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SettleMint, and nothing reaches the server without passing your rules. This is the rule we recommend for hasura-mutations:
{
"version": "1",
"default": "deny",
"tools": {
"hasura-mutations": {
"limits": [
{
"counter": "hasura-mutations_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}hasura-mutations 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.
hasura-mutations. It is categorised as a Write tool in the SettleMint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SettleMint MCP server in PolicyLayer and add a rule for hasura-mutations: 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 SettleMint. Nothing to install.
hasura-mutations 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 hasura-mutations 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 hasura-mutations. 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.
hasura-mutations is provided by the SettleMint MCP server (settlemint/sdk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SettleMint, 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.
55 SettleMint tools catalogued and risk-classified — across an index of 43,000+ MCP servers.