adaptercloud_drift_record
Record a configuration-drift finding for a resource at a given attribute path, capturing expected vs observed values.
This record as markdown: /tools/burdenoff-adaptercloud-mcp/adaptercloud-drift-record.md
What adaptercloud_drift_record does on Adaptercloud
AI agents call adaptercloud_drift_record to retrieve information from Adaptercloud without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
severity | string | — | Severity of the drift |
resourceId | string | Yes | Drifted resource ID |
attributePath | string | Yes | Attribute path that drifted, e.g. "tags.env" |
expectedValue | object | — | Expected value JSON |
observedValue | object | — | Observed value JSON |
Parameters from the server's own tool schema.
Why adaptercloud_drift_record is rated Low
Even though adaptercloud_drift_record only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs adaptercloud_drift_record safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adaptercloud, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For adaptercloud_drift_record, this is the rule to start with:
adaptercloud_drift_record is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Adaptercloud, apply this rule, and every adaptercloud_drift_record call is checked against it from then on.
Questions about adaptercloud_drift_record
Record a configuration-drift finding for a resource at a given attribute path, capturing expected vs observed values. It is categorised as a Read tool in the Adaptercloud MCP Server, which means it retrieves data without modifying state.
adaptercloud_drift_record accepts 5 parameters: severity, resourceId, attributePath, expectedValue, observedValue. Required: resourceId, attributePath. The full parameter table on this page comes from the server's own tool schema.
Register the Adaptercloud MCP server in PolicyLayer and add a rule for adaptercloud_drift_record: 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 Adaptercloud. Nothing to install.
adaptercloud_drift_record is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the adaptercloud_drift_record 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 adaptercloud_drift_record. 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.
adaptercloud_drift_record is provided by the Adaptercloud MCP server (@burdenoff/adaptercloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adaptercloud, and thousands of servers like it.
This server
Across the catalogue