AI agents use adr to create or update resources in Kb — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kb environment.
ADR (Architecture Decision Record) tools typically create or update decision record documents, which would be a Write operation. However, the description is empty, so this is inferred from common convention and the server context of 'note storage' and 'persistent knowledge'. Confidence is low due to lack of description.
From the tool's definition Tool name 'adr' likely refers to Architecture Decision Records; description is empty and uninformative.
Attacks that exploit this kind of access
adr. It is categorised as a Write tool in the Kb MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kb MCP server in PolicyLayer and add a rule for adr: 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 Kb. Nothing to install.
adr 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 adr 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 adr. 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.
adr is provided by the Kb MCP server (okash1n/kb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →