AI agents call adr_diagram to retrieve information from Mcp Adr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool produces a diagram (output) from existing ADR data. While 'generate' might suggest computation, the diagram is a read-only representation of ADR information. There is no data modification, deletion, code execution, or external effects. The tool serves a query/retrieval purpose similar to fetching a formatted view of data.
From the tool's definition 'Generate or retrieve a diagram for an ADR' — the tool retrieves or generates a visualization artifact without modifying the underlying ADR data or triggering external operations.
Attacks that exploit this kind of access
Generate or retrieve a diagram for an ADR. It is categorised as a Read tool in the Mcp Adr MCP Server, which means it retrieves data without modifying state.
Register the Mcp Adr MCP server in PolicyLayer and add a rule for adr_diagram: 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_diagram 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 adr_diagram 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_diagram. 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_diagram 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 →