AI agents call list_adrs to retrieve information from Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about Architecture Decision Records from the knowledge base. The verbs 'list' and 'shows' with filtering capabilities are characteristic of Read operations. There are no side effects, no data modification, no code execution, and no irreversible actions. The blast radius of misuse is minimal—an agent could only access information already stored in the system.
From the tool's definition Tool name 'list_adrs' and description 'List all Architecture Decision Records. Shows ADR number, title, status, and linked dimensions.
Attacks that exploit this kind of access
List all Architecture Decision Records. Shows ADR number, title, status, and linked dimensions. Filter by status or dimension. It is categorised as a Read tool in the Brain MCP Server, which means it retrieves data without modifying state.
Register the Brain MCP server in PolicyLayer and add a rule for list_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 Brain. Nothing to install.
list_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 list_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 list_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.
list_adrs is provided by the Brain MCP server (markschaake/brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_adrs is one line of Brain's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →