MCP integration

Action security for MCP.

Evaluate tool calls before a host or gateway forwards them.

Get the package and source.

Connect the execution boundary.

Use the MCP host forwarding boundary or documented gateway. Only traffic routed through that boundary receives its policy decision.

An example to test

A remote tool request attempts to apply an unexpected patch. Evaluate the selected server, tool and final arguments before forwarding.

Illustrative workflow, not a customer deployment or a measured result.

Before connecting live policy

  1. Identify the handler that actually performs the side effect.
  2. Provide trusted identity, purpose and final action arguments.
  3. Configure the tenant’s assigned runtime and keep API credentials server-side.
  4. Test allowed, blocked and unavailable paths before production.

Integration example

Adapt this existing SDK pattern to your application. Names such as the agent, handler and session refer to your own objects. Follow the package documentation for compatible versions and complete setup.

# Install MCP host / gateway support.
python -m pip install "agenticdome-python-sdk[mcp]"

from agenticdome_sdk.mcp_host import AgenticDomeMCPHostFirewall

firewall = AgenticDomeMCPHostFirewall()
result = await firewall.forward_with_firewall(
    mcp_request=request, context=context, forward_to_third_party=forward_to_mcp_server
)

agenticdome-demo --framework mcp --scenario remote_patch

Python demo commands evaluate fixed inputs against a bundled local policy; they do not instantiate the selected framework or prove a live integration. The TypeScript client and OpenClaw runtime plugin need their documented tenant configuration.

See the decision before the action.

Try a local scenario, then bring your workflow to a deployment review. Start with one agent and one tool, and see exactly where the action can be stopped.