discussion_start · Lockstep MCP: Risk & Policy

WHAT IT DOES

What discussion_start does on Lockstep

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

WHY IT NEEDS A POLICY

Why discussion_start needs a policy

This tool creates a new discussion thread, which is a reversible write operation. It does not execute code, delete data, or involve financial transactions. The blast radius is low since misuse would at worst create unwanted discussion threads that can be cleaned up (given sibling tools like discussion_archive and discussion_cleanup exist).

From the tool's definition 'Start a new discussion thread' — creates a new discussion record in the shared coordination system

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

discussion_start Rate-limited

discussion_start 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": {
    "discussion_start": {
      "limits": [
        {
          "counter": "discussion_start_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 Lockstep, so you can run agents against it safely.

FAQ

Questions about discussion_start

What does the discussion_start tool do? +

Start a new discussion thread. Use this when you need input from other agents or want to discuss an architectural/implementation decision. It is categorised as a Write tool in the Lockstep MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on discussion_start? +

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

What risk level is discussion_start? +

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

Can I rate-limit discussion_start? +

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

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

discussion_start is provided by the Lockstep MCP server (tmmoore286/lockstep-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.