share_experience · Agent-Comm-Hub MCP: Risk & Policy

WHAT IT DOES

What share_experience does on Agent-Comm-Hub

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

WHY IT NEEDS A POLICY

Why share_experience needs a policy

The tool creates new data entries in a shared knowledge base accessible to multiple agents. While not destructive or reversible in a strict sense, it involves modifying shared state and publishing information that persists and affects other agents' decision-making. The lack of approval requirement increases risk of information pollution or manipulation.

From the tool's definition Tool description indicates publishing/sharing experiences directly without approval ('经验直接发布（不需审批）'), making data available to all agents. This is a write operation that creates or modifies shared data in the Hub.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

share_experience Rate-limited

share_experience 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": {
    "share_experience": {
      "limits": [
        {
          "counter": "share_experience_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 Agent-Comm-Hub, so you can run agents against it safely.

FAQ

Questions about share_experience

What does the share_experience tool do? +

分享经验到 Hub。经验直接发布（不需审批），所有 Agent 可见。适合记录踩坑经验、最佳实践。. It is categorised as a Write tool in the Agent-Comm-Hub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on share_experience? +

Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for share_experience: 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 Agent-Comm-Hub. Nothing to install.

What risk level is share_experience? +

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

Can I rate-limit share_experience? +

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

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

share_experience is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.