Run a command in a persistent shell session. Unlike workspace_exec which starts a fresh shell for each command, this maintains state (cwd, env vars, shell history) across calls within the same session. Use sessionId to manage multiple parallel sessions (e.g. one for building, one for testing). Th...
Risk signalsAccepts freeform code/query input (command)
Part of the ArcAgent MCP server.
Free to start. No card required.
AI agents invoke workspace_shell to trigger processes or run actions in ArcAgent MCP. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
workspace_shell can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"workspace_shell": {
"limits": [
{
"counter": "workspace_shell_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full ArcAgent MCP policy for all 45 tools.
These attack patterns abuse exactly the kind of access workspace_shell gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Run a command in a persistent shell session. Unlike workspace_exec which starts a fresh shell for each command, this maintains state (cwd, env vars, shell history) across calls within the same session. Use sessionId to manage multiple parallel sessions (e.g. one for building, one for testing). The repository is at /workspace.. It is categorised as a Execute tool in the ArcAgent MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ArcAgent MCP server in PolicyLayer and add a rule for workspace_shell: 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 ArcAgent MCP. Nothing to install.
workspace_shell 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 workspace_shell 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 workspace_shell. 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.
workspace_shell is provided by the ArcAgent MCP server (araujota/arcagent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 45 ArcAgent MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.