conduit_ingest · Conduit MCP: Risk & Policy

WHAT IT DOES

What conduit_ingest does on Conduit MCP

AI agents use conduit_ingest 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_ingest needs a policy

This tool creates/inserts data into streams reversibly. While event ingestion itself is a write operation, the medium severity reflects that schema auto-detection could lead to unintended schema changes if malicious events are ingested, and large volumes of ingested events could impact system resources or downstream consumers.

From the tool's definition Tool sends/ingests events to streams with auto-detection and schema evolution ('Send one or more events (JSON objects) to a stream. Schema is auto-detected and evolves')

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

conduit_ingest Rate-limited

conduit_ingest 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_ingest": {
      "limits": [
        {
          "counter": "conduit_ingest_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_ingest

What does the conduit_ingest tool do? +

Send one or more events (JSON objects) to a stream. Schema is auto-detected and evolves. 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_ingest? +

Register the Conduit MCP server in PolicyLayer and add a rule for conduit_ingest: 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_ingest? +

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

Can I rate-limit conduit_ingest? +

Yes. Add a rate_limit block to the conduit_ingest 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_ingest completely? +

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

conduit_ingest 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.