Convert downloaded PDF/HTML to notes/text and index the corpus.
AI agents use convert_and_index 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 or modifies data (converting documents into indexed text/notes) but does not delete or irreversibly destroy data, nor does it execute arbitrary code or move funds. The modifications are reversible (indices can be rebuilt, notes regenerated).
From the tool's definition Tool description states it converts PDFs/HTML to notes/text and indexes the corpus. 'Convert' and 'index' involve creating new data structures (notes, indexed corpus) that modify the local knowledge base.
Attacks that exploit this kind of access
Convert downloaded PDF/HTML to notes/text and index the 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 convert_and_index: 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.
convert_and_index 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 convert_and_index 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 convert_and_index. 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.
convert_and_index 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 →