List deliverables from the phase-by-phase taxonomy (Layer 3-5 nodes).
AI agents call list_deliverables to retrieve information from Procurement Graph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and presents existing deliverables data from a taxonomic structure without creating, modifying, deleting, or executing any operations. It is a pure read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name contains 'list' and description states it 'List deliverables from the phase-by-phase taxonomy'. This is a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List deliverables from the phase-by-phase taxonomy (Layer 3-5 nodes). It is categorised as a Read tool in the Procurement Graph MCP Server, which means it retrieves data without modifying state.
Register the Procurement Graph MCP server in PolicyLayer and add a rule for list_deliverables: 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 Procurement Graph. Nothing to install.
list_deliverables 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 list_deliverables 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 list_deliverables. 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.
list_deliverables is provided by the Procurement Graph MCP server (mfbaig35r/procurement-graph). 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 →