AI agents use adr_update_status to create or update resources in Mcp Adr — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Adr environment.
This tool modifies the state/metadata of an ADR record without deleting it or triggering external execution. Status changes are write operations that can be reverted. The severity is medium because misuse could corrupt important architectural decision records and affect team decision-making, but the data remains recoverable.
From the tool's definition Tool name 'adr_update_status' and description 'Change the status of an existing ADR' indicate modification of existing data. The action is reversible—changing a status can be undone by changing it again.
Attacks that exploit this kind of access
Change the status of an existing ADR. It is categorised as a Write tool in the Mcp Adr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Adr MCP server in PolicyLayer and add a rule for adr_update_status: 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 Mcp Adr. Nothing to install.
adr_update_status 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_update_status 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_update_status. 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_update_status is provided by the Mcp Adr MCP server (mauriziomocci/mcp-adr). 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 →