// MCP TOOL REFERENCE

run_shell

Execute shell commands

Accepts freeform code/query input (command)

Part of the Computer-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_shell to trigger processes or run actions in Computer-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_SHELL

run_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. 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.

jjbot1-computer-mcp.yaml

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

See the full Computer-mcp policy for all 12 tools.

// DETAILS

Tool Name run_shell

Category Execute

MCP Server Computer-mcp MCP Server

Risk Level High

// MORE COMPUTER-MCP TOOLS

Execute run_javascript Execute run_python Read get_binance_price Read get_chain_tvl Read get_crypto_markets Read get_crypto_trending Read get_defi_tvl Read get_defi_yields

View all 12 tools →

// WHAT CAN GO WRONG

Agents calling execute-class tools like run_shell 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_shell is one of the high-risk operations in Computer-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_shell tool do? +

Execute shell commands. It is categorised as a Execute tool in the Computer-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_shell? +

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

What risk level is run_shell? +

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

Can I rate-limit run_shell? +

Yes. Add a rate_limit block to the run_shell 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_shell completely? +

Set action: deny in the Intercept policy for run_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.

What MCP server provides run_shell? +

run_shell is provided by the Computer-mcp MCP server (jjbot1/Computer-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

run_shell

Enforce policies on Computer-mcp