list_workflows
AI agents call list_workflows 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 'list_workflows' tool retrieves or enumerates existing workflows without modifying them. This is a standard read operation typical of configuration/metadata APIs. The sibling tools confirm this server's pattern of separating read operations (list_*, get_*) from write/execute (run_workflow, cancel_job) and destructive (delete_workflow) operations. No side effects or data modification occurs.
From the tool's definition Tool name 'list_workflows' with sibling tools 'get_destination_info', 'get_job_info', 'get_source_info', 'get_workflow_info' and 'list_destinations', 'list_jobs', 'list_sources' all follow the 'list' and 'get' pattern indicating data retrieval operations.
Attacks that exploit this kind of access
list_workflows. 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_workflows: 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_workflows 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_workflows 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_workflows. 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_workflows 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 →