Semantic search across all documents in Paperless-ngx.
AI agents call papercortex_search to retrieve information from PaperCortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries document data without side effects. It does not create, modify, delete, or execute operations. The semantic search functionality is purely informational and read-only, making it the lowest-risk category.
From the tool's definition Tool performs 'semantic search across all documents' with no modification, deletion, or execution capabilities described. Search and retrieval operations are non-destructive read operations.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access papercortex_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PaperCortex, and nothing reaches the server without passing your rules. This is the rule we recommend for papercortex_search:
{
"version": "1",
"default": "deny",
"tools": {
"papercortex_search": {}
}
}papercortex_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Semantic search across all documents in Paperless-ngx. It is categorised as a Read tool in the PaperCortex MCP Server, which means it retrieves data without modifying state.
Register the PaperCortex MCP server in PolicyLayer and add a rule for papercortex_search: 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 PaperCortex. Nothing to install.
papercortex_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the papercortex_search 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 papercortex_search. 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.
papercortex_search is provided by the PaperCortex MCP server (renefichtmueller/papercortex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PaperCortex, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 PaperCortex tools catalogued and risk-classified — across an index of 43,000+ MCP servers.