Send input to a running process session. Input is written to the process stdin.
AI agents invoke interact_with_process to trigger actions in OODA Computer Control. 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.
This tool sends arbitrary input to a running process via stdin, which can control the behavior of that process in arbitrary ways — including executing commands, changing program state, or triggering destructive operations. It is an Execute-category action because it drives external process execution, and severity is high given that misuse could manipulate any running process on the system.
From the tool's definition Send input to a running process session. Input is written to the process stdin.
Documented attack patterns abuse exactly the kind of access interact_with_process gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OODA Computer Control, and nothing reaches the server without passing your rules. This is the rule we recommend for interact_with_process:
{
"version": "1",
"default": "deny",
"tools": {
"interact_with_process": {
"limits": [
{
"counter": "interact_with_process_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}interact_with_process 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.
Free to start. No card required.
Send input to a running process session. Input is written to the process stdin. It is categorised as a Execute tool in the OODA Computer Control MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OODA Computer Control MCP server in PolicyLayer and add a rule for interact_with_process: 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 OODA Computer Control. Nothing to install.
interact_with_process 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 interact_with_process 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 interact_with_process. 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.
interact_with_process is provided by the OODA Computer Control MCP server (mnehmos/mnehmos.ooda.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OODA Computer Control, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
99 OODA Computer Control tools catalogued and risk-classified — across an index of 43,000+ MCP servers.