Upload a file
AI agents use ira_upload to create or update resources in IRA-RESEARCHER — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your IRA-RESEARCHER environment.
File upload is a write operation that creates new data or modifies existing data on a server. While not inherently destructive or financial, it carries medium severity because an AI agent could be manipulated into uploading malicious files, sensitive data, or large payloads to unintended destinations.
From the tool's definition Tool name is 'ira_upload' with description 'Upload a file'. The action of uploading is a write operation that creates or modifies data on a remote system.
Attacks that exploit this kind of access
Upload a file. It is categorised as a Write tool in the IRA-RESEARCHER MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the IRA-RESEARCHER MCP server in PolicyLayer and add a rule for ira_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 IRA-RESEARCHER. Nothing to install.
ira_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 ira_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 ira_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.
ira_upload is provided by the IRA-RESEARCHER MCP server (neuralnexustech/ira-researcher). 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 →