onboard_agent · Kontexta MCP: Risk & Policy

WHAT IT DOES

What onboard_agent does on Kontexta

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

WHY IT NEEDS A POLICY

Why onboard_agent needs a policy

This tool creates or modifies workflow rules—configuration data that persists and affects subsequent operations. It is reversible (updates can be undone via git in this git-backed system), placing it in Write rather than Destructive.

From the tool's definition Tool description states it will 'Write or update the kontexta workflow rules block in a project', which modifies configuration that controls agent behavior and execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

onboard_agent Rate-limited

onboard_agent 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": {
    "onboard_agent": {
      "limits": [
        {
          "counter": "onboard_agent_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 Kontexta, so you can run agents against it safely.

FAQ

Questions about onboard_agent

What does the onboard_agent tool do? +

Write or update the kontexta workflow rules block in a project. It is categorised as a Write tool in the Kontexta MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on onboard_agent? +

Register the Kontexta MCP server in PolicyLayer and add a rule for onboard_agent: 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 Kontexta. Nothing to install.

What risk level is onboard_agent? +

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

Can I rate-limit onboard_agent? +

Yes. Add a rate_limit block to the onboard_agent 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 onboard_agent completely? +

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

onboard_agent is provided by the Kontexta MCP server (safiyu/kontexta). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.