Create a relationship between two ADRs: related_to, conflicts_with, or depends_on
AI agents use link_adrs to create or update resources in Adr Skills — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Adr Skills environment.
This tool creates or modifies metadata by establishing links between Architecture Decision Records. While it does not delete data (thus not Destructive) or execute arbitrary code (thus not Execute), it does write new relationship data into the system.
From the tool's definition Tool description states 'Create a relationship between two ADRs' with relationship types (related_to, conflicts_with, depends_on). The verb 'Create' and the action of establishing new relationships indicates data modification rather than retrieval.
Attacks that exploit this kind of access
Create a relationship between two ADRs: related_to, conflicts_with, or depends_on. It is categorised as a Write tool in the Adr Skills MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Adr Skills MCP server in PolicyLayer and add a rule for link_adrs: 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.
link_adrs is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the link_adrs 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 link_adrs. 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.
link_adrs 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 →