multi_turn_edit
AI agents use multi_turn_edit to create or update resources in Academic Figures — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Academic Figures environment.
This tool modifies academic figure content in a reversible manner (edits can be undone), consistent with Write category. The medium severity reflects that misuse could corrupt publication-quality figures or create misleading scientific visualizations, but changes are not permanent or destructive.
From the tool's definition Tool name 'multi_turn_edit' combined with sibling tools 'edit_figure' and 'generate_figure' indicates it modifies figure data. The 'multi_turn' prefix suggests iterative editing of academic figures.
Attacks that exploit this kind of access
multi_turn_edit. It is categorised as a Write tool in the Academic Figures MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Academic Figures MCP server in PolicyLayer and add a rule for multi_turn_edit: 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 Academic Figures. Nothing to install.
multi_turn_edit 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 multi_turn_edit 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 multi_turn_edit. 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.
multi_turn_edit is provided by the Academic Figures MCP server (u9401066/academic-figures-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 →