List available sources from the Unstructured API.
AI agents call list_sources to retrieve information from Unstructured API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only query operation to enumerate available source connectors (S3, Azure, Google Drive, etc.). It has no side effects, does not modify state, and simply returns information. This is the clearest example of a Read category tool. Severity is low because listing sources poses minimal risk even if misused—an agent cannot cause damage or unintended side effects through enumeration alone.
From the tool's definition Tool name is 'list_sources' and description states 'List available sources from the Unstructured API.' This is a retrieval operation that queries and returns data without modifying anything.
Attacks that exploit this kind of access
List available sources from the Unstructured API. It is categorised as a Read tool in the Unstructured API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Unstructured API MCP Server MCP server in PolicyLayer and add a rule for list_sources: 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 Unstructured API MCP Server. Nothing to install.
list_sources 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_sources 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_sources. 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_sources is provided by the Unstructured API MCP Server MCP server (liuchongchong1995/uns-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 →