ariba_reject_sourcing_task
AI agents use ariba_reject_sourcing_task to create or update resources in SAP Ariba MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SAP Ariba MCP Server environment.
Based on context from related approval/denial tools in the same server that modify document states, this tool likely changes a sourcing task's status from pending to rejected—a reversible modification operation (Write category).
From the tool's definition Tool name 'ariba_reject_sourcing_task' indicates modification of a sourcing task status through rejection. Sibling tools in the approval workflow (approve, deny, list approvables) all modify procurement document states.
Attacks that exploit this kind of access
ariba_reject_sourcing_task. It is categorised as a Write tool in the SAP Ariba MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SAP Ariba MCP Server MCP server in PolicyLayer and add a rule for ariba_reject_sourcing_task: 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_reject_sourcing_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the ariba_reject_sourcing_task 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_reject_sourcing_task. 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_reject_sourcing_task 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 →