submit
AI agents use submit to create or update resources in Acatome Quest — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Acatome Quest environment.
The 'submit' tool creates or registers a new paper request (DOI, arXiv, etc.) in the system. This is a Write operation—it modifies state by recording a new submission, though the action is reversible via update/status tools. It is not Destructive (nothing is deleted), Execute (no arbitrary code execution), or Financial.
From the tool's definition Tool named 'submit' in a server that handles paper requests and file submissions. Sibling tools include 'submit_file' and 'update', and the server description mentions 'tools for submission, status, update, and file upload.' The name 'submit' suggests…
Attacks that exploit this kind of access
submit. It is categorised as a Write tool in the Acatome Quest MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Acatome Quest MCP server in PolicyLayer and add a rule for submit: 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 Acatome Quest. Nothing to install.
submit 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 submit 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 submit. 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.
submit is provided by the Acatome Quest MCP server (retospect/acatome-quest-mcp). 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 →