daa_knowledge_share · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What daa_knowledge_share does on Claude Flow

AI agents use daa_knowledge_share 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 daa_knowledge_share needs a policy

The tool writes/propagates knowledge state across multiple agents in the swarm. It modifies the cognitive/knowledge state of agents, which is a reversible write operation. It does not execute code, delete data, or involve financial transactions. Misuse could corrupt shared knowledge across the swarm, giving it a medium severity.

From the tool's definition 'Share knowledge between agents' and 'share knowledge across the swarm' — the tool creates/transmits data between agents in the swarm.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

daa_knowledge_share Rate-limited

daa_knowledge_share 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": {
    "daa_knowledge_share": {
      "limits": [
        {
          "counter": "daa_knowledge_share_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 daa_knowledge_share

What does the daa_knowledge_share tool do? +

Share knowledge between agents Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For static one-shot agents, native Task is fine. 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 daa_knowledge_share? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for daa_knowledge_share: 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 daa_knowledge_share? +

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

Can I rate-limit daa_knowledge_share? +

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

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

daa_knowledge_share 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.