AI agents call adr_dependencies 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 reads and analyzes existing ADR relationships to construct a dependency graph. It retrieves/queries data about ADR dependencies without creating, modifying, or deleting any records. The operation is purely informational.
From the tool's definition "Build the dependency graph of ADRs, optionally filtered to one ADR's transitive deps"
Attacks that exploit this kind of access
Build the dependency graph of ADRs, optionally filtered to one ADR's transitive deps. 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_dependencies: 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_dependencies 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_dependencies 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_dependencies. 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_dependencies 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 →