Assemble all sections, figures, tables, and references into
AI agents use build_docx to create or update resources in Q1 Crafter MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Q1 Crafter MCP environment.
This tool assembles research content into a formatted .docx document, which is a file creation/write operation. It produces a new output artifact but does not execute code, delete data, or involve financial transactions. The description is truncated, slightly lowering confidence, but the server description confirms it produces 'APA 7 formatted .docx output'.
From the tool's definition 'Assemble all sections, figures, tables, and references into' — implies creating/writing a .docx output file
Attacks that exploit this kind of access
Assemble all sections, figures, tables, and references into. It is categorised as a Write tool in the Q1 Crafter MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Q1 Crafter MCP server in PolicyLayer and add a rule for build_docx: 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 Q1 Crafter MCP. Nothing to install.
build_docx 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 build_docx 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 build_docx. 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.
build_docx is provided by the Q1 Crafter MCP server (muslus/q1-crafter-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 →