conduit_add_forward · Conduit MCP: Risk & Policy

WHAT IT DOES

What conduit_add_forward does on Conduit MCP

AI agents use conduit_add_forward to create or update resources in Conduit MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Conduit MCP environment.

WHY IT NEEDS A POLICY

Why conduit_add_forward needs a policy

This tool writes configuration data to the system by adding forwarding rules to streams. While it modifies system behavior and routing, the action is reversible (destinations can be removed). It does not delete data, execute arbitrary code, or move money, so it falls into Write category.

From the tool's definition Add a forwarding destination to a stream. The tool creates or modifies stream configuration by adding a new forward destination (HTTP webhooks, MQTT brokers, WebSocket endpoints), which is a reversible configuration change.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

conduit_add_forward Rate-limited

conduit_add_forward stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "conduit_add_forward": {
      "limits": [
        {
          "counter": "conduit_add_forward_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Conduit MCP, so you can run agents against it safely.

FAQ

Questions about conduit_add_forward

What does the conduit_add_forward tool do? +

Add a forwarding destination to a stream. Supports HTTP webhooks, MQTT brokers, and WebSocket endpoints. Events are forwarded in real-time. It is categorised as a Write tool in the Conduit MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on conduit_add_forward? +

Register the Conduit MCP server in PolicyLayer and add a rule for conduit_add_forward: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Conduit MCP. Nothing to install.

What risk level is conduit_add_forward? +

conduit_add_forward is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit conduit_add_forward? +

Yes. Add a rate_limit block to the conduit_add_forward rule in your PolicyLayer 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 conduit_add_forward completely? +

Set action: deny in the PolicyLayer policy for conduit_add_forward. 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 conduit_add_forward? +

conduit_add_forward is provided by the Conduit MCP server (useconduit/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.