Search past architectural decisions by keyword
AI agents call search_decisions 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 only retrieves and queries existing architectural decision records based on search criteria. It has no side effects, cannot modify or delete data, and cannot execute code or trigger external operations. It falls squarely into the Read category with low severity since misuse would only expose information already stored in the ADR database, with minimal blast radius.
From the tool's definition Tool description states it 'Search[es] past architectural decisions by keyword' - a query operation with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search past architectural decisions by keyword. 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 search_decisions: 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.
search_decisions 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 search_decisions 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 search_decisions. 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.
search_decisions 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 →