tf_activity · decoupler- MCP: Risk & Policy

WHAT IT DOES

What tf_activity does on decoupler-MCP

AI agents invoke tf_activity to trigger actions in decoupler-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 tf_activity needs a policy

This tool executes a bioinformatics computation (TF activity inference via decoupleR) against loaded datasets. It does not simply retrieve stored data; it triggers an analytical algorithm that produces derived results. No financial, destructive, or write side-effects are evident, so Execute is the most appropriate category.

From the tool's definition Transcription factor activity inference — runs a computational inference pipeline (part of the decoupleR framework) over single-cell RNA-Seq data

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tf_activity Rate-limited

tf_activity 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": {
    "tf_activity": {
      "limits": [
        {
          "counter": "tf_activity_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 decoupler-MCP, so you can run agents against it safely.

FAQ

Questions about tf_activity

What does the tf_activity tool do? +

Transcription factor activity inference. It is categorised as a Execute tool in the decoupler-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 tf_activity? +

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

What risk level is tf_activity? +

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

Can I rate-limit tf_activity? +

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

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

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