AI agents call list_documents to retrieve information from Oblio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query operation that retrieves document metadata without creating, modifying, or deleting data. The use of GET HTTP method and the 'list' action confirm it has no side effects. In the context of an accounting system, listing documents is a read-only operation with minimal blast radius if misused by an agent.
From the tool's definition Tool performs GET request to list documents with filters and pagination; 'Lists documents from Oblio via GET /api/docs/{type}/list' explicitly indicates retrieval without modification.
Attacks that exploit this kind of access
Lists documents from Oblio via GET /api/docs/{type}/list with filters and pagination. It is categorised as a Read tool in the Oblio MCP Server, which means it retrieves data without modifying state.
Register the Oblio MCP server in PolicyLayer and add a rule for list_documents: 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 Oblio. Nothing to install.
list_documents 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 list_documents 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 list_documents. 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.
list_documents is provided by the Oblio MCP server (valentinludu/oblio-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 →