This record as markdown: /tools/io-github-portel-dev-ncp/exec-async.md
What exec_async does on Ncp
AI agents invoke exec_async to trigger actions in Ncp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why exec_async is rated High
Shell command execution is a quintessential Execute category tool—it runs code whose effects depend entirely on the command arguments. Asynchronous execution does not change the severity; an attacker or misguided agent could execute destructive commands (rm -rf /, data exfiltration, credential theft, lateral movement). Critical severity reflects the virtually unlimited blast radius of shell access.
From the tool's definition Tool name 'exec_async' combined with description 'Execute shell command asynchronously' explicitly indicates execution of arbitrary shell commands.
Attacks that exploit this kind of access
The rule that runs exec_async safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For exec_async, this is the rule to start with:
exec_async stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every exec_async call is checked against it from then on.
Questions about exec_async
Execute shell command asynchronously. It is categorised as a Execute tool in the Ncp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ncp MCP server in PolicyLayer and add a rule for exec_async: 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 Ncp. Nothing to install.
exec_async is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the exec_async 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 exec_async. 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.
exec_async is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue