// MCP TOOL REFERENCE

workspace_exec

Run a shell command in your development workspace. The repository is at /workspace. Commands run as non-root user. Use for building, testing, installing packages, running scripts.

Accepts freeform code/query input (command); Admin/system-level operation

Part of the ArcAgent MCP MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

arcagent-mcp Execute Risk 4/5

// WHEN AI AGENTS USE THIS TOOL

AI agents invoke workspace_exec 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.

// WHY ENFORCE A POLICY ON WORKSPACE_EXEC

workspace_exec can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.

// RECOMMENDED POLICY

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

arcagent-mcp.yaml

tools:
  workspace_exec:
    rules:
      - action: allow
        rate_limit:
          max: 10
          window: 60
        validate:
          required_args: true

See the full ArcAgent MCP policy for all 45 tools.

// DETAILS

Tool Name workspace_exec

Category Execute

MCP Server ArcAgent MCP MCP Server

Risk Level High

// MORE ARCAGENT MCP TOOLS

Destructive cancel_bounty Execute rate_agent Execute workspace_crash_reports Execute workspace_exec_stream Execute workspace_shell Write create_bounty Write import_work_item Write register_account

View all 45 tools →

// WHAT CAN GO WRONG

Agents calling execute-class tools like workspace_exec have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER EXECUTE TOOLS ACROSS MCP SERVERS

Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

Agent Passport System — Cryptographic Identity for AI Agents commerce_preflight Agent Passport System — Cryptographic Identity for AI Agents execute_with_context Agent Passport System — Cryptographic Identity for AI Agents gateway_execute_approval Agent Passport System — Cryptographic Identity for AI Agents governance_360 Agent Passport System — Cryptographic Identity for AI Agents parse_governance_block_html AgentClear — API Marketplace for AI Agents call_service

// IN CONTEXT OF HIGH RISK

workspace_exec is one of the high-risk operations in ArcAgent MCP. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the workspace_exec tool do? +

Run a shell command in your development workspace. The repository is at /workspace. Commands run as non-root user. Use for building, testing, installing packages, running scripts.. 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.

How do I enforce a policy on workspace_exec? +

Add a rule in your Intercept YAML policy under the tools section for workspace_exec. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the ArcAgent MCP MCP server.

What risk level is workspace_exec? +

workspace_exec is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit workspace_exec? +

Yes. Add a rate_limit block to the workspace_exec rule in your Intercept 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.

How do I block workspace_exec completely? +

Set action: deny in the Intercept policy for workspace_exec. 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.

What MCP server provides workspace_exec? +

workspace_exec is provided by the ArcAgent MCP MCP server (arcagent-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

workspace_exec

Enforce policies on ArcAgent MCP