Download open-access full texts and write manual follow-up list.
AI agents use download_fulltexts 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 both downloads files (creating new local data) and writes a follow-up list, constituting a Write operation. It creates/modifies data on the local system but is reversible (files can be deleted). The blast radius is medium since it could download large volumes of content or write files to unexpected locations if misused.
From the tool's definition Download open-access full texts and write manual follow-up list
Attacks that exploit this kind of access
Download open-access full texts and write manual follow-up list. 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 download_fulltexts: 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.
download_fulltexts 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 download_fulltexts 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 download_fulltexts. 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.
download_fulltexts 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 →