Explain which accepted ADRs apply before creating code (auth, payments, currency, etc.).
AI agents call explain_architectural_decisions to retrieve information from BLUEPRINT MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns architectural decision records to inform coding decisions. It retrieves existing data (ADRs) without modifying, deleting, or executing operations. The advisory-first guidance nature confirms it is informational only. No destructive, financial, or execution-level risk.
From the tool's definition Tool description states 'Explain which accepted ADRs apply' — a pure lookup/query operation. The name uses 'explain' and sibling tools include 'list_architectural_decisions' and 'find_existing_abstractions', confirming this is a retrieval function with no…
Attacks that exploit this kind of access
Explain which accepted ADRs apply before creating code (auth, payments, currency, etc.). It is categorised as a Read tool in the BLUEPRINT MCP MCP Server, which means it retrieves data without modifying state.
Register the BLUEPRINT MCP server in PolicyLayer and add a rule for explain_architectural_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 BLUEPRINT MCP. Nothing to install.
explain_architectural_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 explain_architectural_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 explain_architectural_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.
explain_architectural_decisions is provided by the BLUEPRINT MCP server (vedv7/blueprint.mcp). 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 →