link_decision
Say that this decision SHAPED a node: a goal, an idea, a scope (initiative/epic), a card (work_item) or an indicator. An edge with a reason; the target does not change. Linking a pair that is already linked replaces the reason (an upsert). The reason is recorded on the link and doubles as the aud...
This record as markdown: /tools/adrata-adrata-mcp/link-decision.md
What link_decision does on Adrata
AI agents call link_decision 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 link_decision is rated Low
Even though link_decision 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 link_decision 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 link_decision, this is the rule to start with:
link_decision 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 link_decision call is checked against it from then on.
Questions about link_decision
Say that this decision SHAPED a node: a goal, an idea, a scope (initiative/epic), a card (work_item) or an indicator. An edge with a reason; the target does not change. Linking a pair that is already linked replaces the reason (an upsert). The reason is recorded on the link 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 link_decision: 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.
link_decision 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 link_decision 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_decision. 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_decision 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