Find Accepted ADRs that have not been reviewed in a while and may need revisiting
AI agents call check_stale_adrs to retrieve information from Adr Skills without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query across stored ADRs to identify those meeting certain criteria (accepted status, age since last review). It returns informational results to help prioritize review work but does not execute code, modify data, delete records, or commit financial transactions. The action of identifying stale records is purely informational with no side effects.
From the tool's definition The tool 'check_stale_adrs' is described as finding and identifying Accepted ADRs that have not been reviewed in a while.
Attacks that exploit this kind of access
Find Accepted ADRs that have not been reviewed in a while and may need revisiting. It is categorised as a Read tool in the Adr Skills MCP Server, which means it retrieves data without modifying state.
Register the Adr Skills MCP server in PolicyLayer and add a rule for check_stale_adrs: 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 Adr Skills. Nothing to install.
check_stale_adrs 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 check_stale_adrs 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 check_stale_adrs. 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.
check_stale_adrs is provided by the Adr Skills MCP server (wooxogh/adr-mcp-setup). 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 →