conduit_backfill · Conduit MCP: Risk & Policy

WHAT IT DOES

What conduit_backfill does on Conduit MCP

AI agents invoke conduit_backfill to trigger actions in Conduit MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why conduit_backfill needs a policy

This tool triggers an external operation (replaying/forwarding historical events to destinations as a background job). It doesn't simply read data—it actively pushes events to forwarding destinations, which constitutes executing an operation with external side effects. It's not purely destructive or financial, but it triggers a potentially large-scale background process whose effects depend on configuration.

From the tool's definition 'Replay historical events from a stream to one or more forwarding destinations. Runs as a background job with progress tracking.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

conduit_backfill Rate-limited

conduit_backfill stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_backfill": {
      "limits": [
        {
          "counter": "conduit_backfill_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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_backfill

What does the conduit_backfill tool do? +

Replay historical events from a stream to one or more forwarding destinations. Runs as a background job with progress tracking. It is categorised as a Execute tool in the Conduit 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 conduit_backfill? +

Register the Conduit MCP server in PolicyLayer and add a rule for conduit_backfill: 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_backfill? +

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

Can I rate-limit conduit_backfill? +

Yes. Add a rate_limit block to the conduit_backfill 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_backfill completely? +

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

conduit_backfill 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.