get_decision_graph

SERVERAdrata SOURCE@adrata/adrata-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/adrata-adrata-mcp/get-decision-graph.md

WHAT IT DOES

What get_decision_graph does on Adrata

AI agents call get_decision_graph 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.

RISK

Why get_decision_graph is rated Low

Even though get_decision_graph 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

RECOMMENDED RULE

The rule that runs get_decision_graph 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 get_decision_graph, this is the rule to start with:

get_decision_graph Allowed

get_decision_graph is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_decision_graph": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Adrata, apply this rule, and every get_decision_graph call is checked against it from then on.

FAQ

Questions about get_decision_graph

What does the get_decision_graph tool do? +

Read the decision GRAPH around one decision: the decisions it relates to and those that relate to it, each edge typed (supersedes | amends | refines | depends_on | conflicts_with | relates_to) with its reason. refines edges are the sub-decisions: a big ruling broken into the smaller calls that implement it. conflicts_with edges are two live rulings the owner has not picked between — read those before acting on either. Use this to walk a decision chain instead of paging through list_decisions. It is categorised as a Read tool in the Adrata MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_decision_graph? +

Register the Adrata MCP server in PolicyLayer and add a rule for get_decision_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 Adrata. Nothing to install.

What risk level is get_decision_graph? +

get_decision_graph is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_decision_graph? +

Yes. Add a rate_limit block to the get_decision_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.

How do I block get_decision_graph completely? +

Set action: deny in the PolicyLayer policy for get_decision_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.

What MCP server provides get_decision_graph? +

get_decision_graph 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.

KEEP EXPLORING

More on Adrata, and thousands of servers like it.

This server

All 395 Adrata tools →

Across the catalogue

get_cocktail_by_category on Cocktails RAG MCP Server →get_file_snippet on ACE-MCP →get_torrent_detail on M-Team MCP Server →get_customer_data on 08-AI-Business-Agent → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →