Resolve an open escalation with a resolution message. Pass project to override .cantrip.json — useful in cloud-hosted or multi-project contexts.
AI agents use cantrip_review_resolve to create or update resources in Cantrip — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cantrip environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | Yes | Escalation ID |
project | string | — | Project slug — overrides .cantrip.json. Required in environments where cantrip_connect cannot write to the filesystem. |
resolution | string | Yes | Resolution text explaining the decision |
Parameters from the server's own tool schema.
The tool creates or updates an escalation record by applying a resolution, which is a data modification. It does not execute arbitrary code, delete data irreversibly, or move money. While resolving an escalation could have downstream GTM consequences, the core operation is a state-change write to a data record.
From the tool's definition Tool description states 'Resolve an open escalation with a resolution message' — this modifies the state of an escalation record from open to resolved, which is a reversible write operation on data within the Cantrip GTM system.
Documented attack patterns abuse exactly the kind of access cantrip_review_resolve gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cantrip, and nothing reaches the server without passing your rules. This is the rule we recommend for cantrip_review_resolve:
{
"version": "1",
"default": "deny",
"tools": {
"cantrip_review_resolve": {
"limits": [
{
"counter": "cantrip_review_resolve_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}cantrip_review_resolve 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.
Resolve an open escalation with a resolution message. Pass project to override .cantrip.json — useful in cloud-hosted or multi-project contexts. It is categorised as a Write tool in the Cantrip MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
cantrip_review_resolve accepts 3 parameters: id, project, resolution. Required: id, resolution. The full parameter table on this page comes from the server's own tool schema.
Register the Cantrip MCP server in PolicyLayer and add a rule for cantrip_review_resolve: 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 Cantrip. Nothing to install.
cantrip_review_resolve 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 cantrip_review_resolve 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 cantrip_review_resolve. 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.
cantrip_review_resolve is provided by the Cantrip MCP server (mcp-server-cantrip). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cantrip, 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.
19 Cantrip tools catalogued and risk-classified — across an index of 43,000+ MCP servers.