Visualize ADR dependency graph. Optionally scope to a single ADR.
AI agents call get_adr_graph 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 queries and displays the dependency relationships between Architecture Decision Records. It is purely informational (Read category), presenting existing data in graph form. There are no side effects, data modifications, destructive actions, or external operations triggered. The optional scoping parameter only filters which data is visualized, not whether data is changed.
From the tool's definition Tool description states 'Visualize ADR dependency graph' - a read-only visualization operation that retrieves and displays existing data without modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Visualize ADR dependency graph. Optionally scope to a single ADR. 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 get_adr_graph: 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.
get_adr_graph 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 get_adr_graph 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 get_adr_graph. 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.
get_adr_graph 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 →