app_list
List installed .0n applications from ~/.0n/apps/. Example: app_list({})
This record as markdown: /tools/io-github-0nork-0nmcp/app-list.md
What app_list does on 0nmcp
AI agents call app_list to retrieve information from 0nmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why app_list is rated Low
This tool retrieves information about installed applications from a local filesystem directory. It performs a query/list operation that does not modify, execute, or delete anything. The action is purely informational and has no external effects beyond returning data to the caller.
From the tool's definition Tool name is 'app_list' and description states it 'List[s] installed .0n applications from ~/.0n/apps/'. The verb 'list' and the read-only nature of querying a local directory for installed applications indicate data retrieval with no side effects.
Attacks that exploit this kind of access
The rule that runs app_list safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0nmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For app_list, this is the rule to start with:
app_list is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 0nmcp, apply this rule, and every app_list call is checked against it from then on.
Questions about app_list
List installed .0n applications from ~/.0n/apps/. Example: app_list({}). It is categorised as a Read tool in the 0nmcp MCP Server, which means it retrieves data without modifying state.
Register the 0n MCP server in PolicyLayer and add a rule for app_list: 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 0nmcp. Nothing to install.
app_list 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 app_list 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 app_list. 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.
app_list is provided by the 0n MCP server (0nmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0n, and thousands of servers like it.
This server
Across the catalogue