// MCP TOOL REFERENCE

run-python-code

Execute Python code in a sandbox.

Accepts freeform code/query input (code)

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

Dumpling-AI/mcp-server-dumplingai Execute Risk 4/5

// WHEN AI AGENTS USE THIS TOOL

AI agents invoke run-python-code to trigger processes or run actions in Dumpling AI MCP Server. 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-PYTHON-CODE

run-python-code 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.

dumpling-ai-mcp-server-dumplingai.yaml

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

See the full Dumpling AI MCP Server policy for all 27 tools.

// DETAILS

Tool Name run-python-code

Category Execute

MCP Server Dumpling AI MCP Server MCP Server

Risk Level High

// MORE DUMPLING AI MCP SERVER TOOLS

Execute run-js-code Write add-to-knowledge-base Write convert-to-pdf Write generate-agent-completion Write generate-ai-image Write merge-pdfs Write write-pdf-metadata Read crawl

View all 27 tools →

// WHAT CAN GO WRONG

Agents calling execute-class tools like run-python-code 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-python-code is one of the high-risk operations in Dumpling AI MCP Server. 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-python-code tool do? +

Execute Python code in a sandbox.. It is categorised as a Execute tool in the Dumpling AI MCP Server 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-python-code? +

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

What risk level is run-python-code? +

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

Can I rate-limit run-python-code? +

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

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

run-python-code is provided by the Dumpling AI MCP Server MCP server (Dumpling-AI/mcp-server-dumplingai). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

run-python-code

Enforce policies on Dumpling AI MCP Server