receipts.upload
AI agents use receipts.upload to create or update resources in Kelnix Receipt Mcp Api — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kelnix Receipt Mcp Api environment.
Based on the tool name, this likely uploads a receipt file to the server, which is a Write operation (creates/stores data). The empty description reduces confidence. Given the sibling tool 'receipts.upload_and_process' exists separately, this tool likely only uploads without processing. Severity is medium as it involves sending potentially sensitive financial documents to an external service.
From the tool's definition Tool name 'receipts.upload' implies uploading data; description is empty and uninformative.
Attacks that exploit this kind of access
receipts.upload. It is categorised as a Write tool in the Kelnix Receipt Mcp Api MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kelnix Receipt Mcp Api MCP server in PolicyLayer and add a rule for receipts.upload: 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 Kelnix Receipt Mcp Api. Nothing to install.
receipts.upload 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 receipts.upload 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 receipts.upload. 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.
receipts.upload is provided by the Kelnix Receipt Mcp Api MCP server (kelnixsolutions/kelnix-receipt-mcp-api). 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 →