relate_decisions
Draw a typed edge from one decision to another. refines = the related decision is a SUB-DECISION of this one (a smaller call that implements the bigger ruling). supersedes = this decision replaces the target, and the target moves to superseded exactly as record_decision with supersedesDecisionId ...
This record as markdown: /tools/adrata-adrata-mcp/relate-decisions.md
What relate_decisions does on Adrata
AI agents call relate_decisions to retrieve information from Adrata without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why relate_decisions is rated Low
Even though relate_decisions only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs relate_decisions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adrata, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For relate_decisions, this is the rule to start with:
relate_decisions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Adrata, apply this rule, and every relate_decisions call is checked against it from then on.
Questions about relate_decisions
Draw a typed edge from one decision to another. refines = the related decision is a SUB-DECISION of this one (a smaller call that implements the bigger ruling). supersedes = this decision replaces the target, and the target moves to superseded exactly as record_decision with supersedesDecisionId does. amends = this one changes part of the target without replacing it. depends_on = this one only holds while the target does. conflicts_with = two LIVE rulings the owner has not picked between — record the conflict rather than silently choosing. relates_to = connected, none of the above. The pair plus the relation is the key: relating the same pair the same way again replaces the reason (an upsert). The reason is recorded on the edge and doubles as the audit reason.${GOVERNED_NOTE}. It is categorised as a Read tool in the Adrata MCP Server, which means it retrieves data without modifying state.
Register the Adrata MCP server in PolicyLayer and add a rule for relate_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 Adrata. Nothing to install.
relate_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 relate_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 relate_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.
relate_decisions is provided by the Adrata MCP server (@adrata/adrata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adrata, and thousands of servers like it.
This server
Across the catalogue