ariba_sourcing_query_view
AI agents call ariba_sourcing_query_view to retrieve information from SAP Ariba MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'ariba_sourcing_query_view' suggests querying or viewing sourcing data, which is a read operation. However, the description is empty, reducing confidence. The 'query' component could imply executing arbitrary queries with broader impact, but 'view' strongly suggests read-only access. Severity is medium given that sourcing data in procurement systems can be sensitive (supplier pricing, bids, contracts).
From the tool's definition Tool name contains 'query' and 'view', suggesting a read/query operation on sourcing data.
Attacks that exploit this kind of access
ariba_sourcing_query_view. It is categorised as a Read tool in the SAP Ariba MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SAP Ariba MCP Server MCP server in PolicyLayer and add a rule for ariba_sourcing_query_view: 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 SAP Ariba MCP Server. Nothing to install.
ariba_sourcing_query_view 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 ariba_sourcing_query_view 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 ariba_sourcing_query_view. 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.
ariba_sourcing_query_view is provided by the SAP Ariba MCP Server MCP server (vanshikadhole/mcpserver). 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 →