Generate an outline and first draft scaffold from the local corpus.
AI agents use write_draft to create or update resources in Literature Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Literature Agent environment.
This tool creates new textual content (draft outlines and scaffolds) based on existing literature data. It is a Write operation because it produces new, reversible content artifacts without executing arbitrary code, deleting data, or causing financial impact.
From the tool's definition Tool name is 'write_draft' and description states it will 'Generate an outline and first draft scaffold from the local corpus.' The verb 'Generate' and the output of 'draft scaffold' indicate content creation.
Attacks that exploit this kind of access
Generate an outline and first draft scaffold from the local corpus. It is categorised as a Write tool in the Literature Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Literature Agent MCP server in PolicyLayer and add a rule for write_draft: 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 Literature Agent. Nothing to install.
write_draft 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 write_draft 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 write_draft. 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.
write_draft is provided by the Literature Agent MCP server (zouxy111/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 →