AI agents invoke siprec_ingest_file to trigger actions in Vcon. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
siprec_ingest_file triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Manually trigger ingestion of a SIPREC XML or JSON file from the watch folder. Useful for testing or re-processing. It is categorised as a Execute tool in the Vcon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vcon MCP server in PolicyLayer and add a rule for siprec_ingest_file: 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 Vcon. Nothing to install.
siprec_ingest_file is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the siprec_ingest_file 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 siprec_ingest_file. 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.
siprec_ingest_file is provided by the Vcon MCP server (vcon-dev/vcon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.