// MCP TOOL REFERENCE

run-command

Run a terminal command

Accepts freeform code/query input (command); Accepts file system path (directory)

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

// WHEN AI AGENTS USE THIS TOOL

AI agents invoke run-command to trigger processes or run actions in React 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 RUN-COMMAND

run-command 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.

streen9-react-mcp.yaml

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

See the full React MCP policy for all 9 tools.

// DETAILS

Tool Name run-command

Category Execute

MCP Server React MCP MCP Server

Risk Level High

// MORE REACT MCP TOOLS

Execute run-react-app Execute stop-process Write create-react-app Write edit-file Write install-package Read get-process-output Read list-processes Read read-file

View all 9 tools →

// WHAT CAN GO WRONG

Agents calling execute-class tools like run-command 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

run-command is one of the high-risk operations in React 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 run-command tool do? +

Run a terminal command. It is categorised as a Execute tool in the React 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 run-command? +

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

What risk level is run-command? +

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

Can I rate-limit run-command? +

Yes. Add a rate_limit block to the run-command 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 run-command completely? +

Set action: deny in the Intercept policy for run-command. 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 run-command? +

run-command is provided by the React MCP MCP server (Streen9/react-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

run-command

Enforce policies on React MCP