communicate · Liana- MCP: Risk & Policy

WHAT IT DOES

What communicate does on Liana-MCP

AI agents invoke communicate to trigger actions in Liana-MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why communicate needs a policy

This tool executes a computational analysis method (CCC analysis) on input data. It doesn't simply read existing data — it runs an analytical algorithm/pipeline that processes data and produces results. This fits Execute as it triggers external operations (statistical/ML computations) whose effects depend on arguments (the chosen method and input data).

From the tool's definition Cell-cell communication analysis with one method (cellphonedb, cellchat, connectome, natmi, etc.) — triggers computational analysis pipelines on scRNA-Seq data

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

communicate Rate-limited

communicate stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "communicate": {
      "limits": [
        {
          "counter": "communicate_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Liana-MCP, so you can run agents against it safely.

FAQ

Questions about communicate

What does the communicate tool do? +

Cell-cell communication analysis with one method (cellphonedb, cellchat, connectome, natmi, etc.). It is categorised as a Execute tool in the Liana-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on communicate? +

Register the Liana- MCP server in PolicyLayer and add a rule for communicate: 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 Liana-MCP. Nothing to install.

What risk level is communicate? +

communicate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit communicate? +

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

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

communicate is provided by the Liana- MCP server (scmcphub/liana-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.