results_merge · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What results_merge does on Claude Flow

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

WHY IT NEEDS A POLICY

Why results_merge needs a policy

The tool merges/combines results, which constitutes creating or modifying data in a reversible manner. CRDT merging is a Write operation—it updates state but does not destroy or execute arbitrary code. Severity is medium because unintended merges in a multi-agent orchestration system could corrupt workflow state or duplicate/lose results, but the operation is theoretically reversible depending on system design.

From the tool's definition Tool name 'results_merge' combined with description 'Merge results with CRDT' indicates modification of data structures using Conflict-free Replicated Data Type semantics.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

results_merge Rate-limited

results_merge 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": {
    "results_merge": {
      "limits": [
        {
          "counter": "results_merge_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about results_merge

What does the results_merge tool do? +

Merge results with CRDT. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on results_merge? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for results_merge: 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 Claude Flow. Nothing to install.

What risk level is results_merge? +

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

Can I rate-limit results_merge? +

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

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

results_merge is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.