take_drug

Take a digital drug to modify your behavior. Each drug has a fixed duration.

SERVERAgent Drugs SOURCE2389-research/agent-drugs

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade A, identity unverified Pull the record →

This record as markdown: /tools/2389-research-agent-drugs/take-drug.md

WHAT IT DOES

What take_drug does on Agent Drugs

AI agents invoke take_drug to trigger actions in Agent Drugs. 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.

RISK

Why take_drug is rated High

This tool performs prompt injection to modify AI behavior, which is an Execute-category action with critical severity. It doesn't merely read or write data — it actively alters the runtime behavior of an AI agent, potentially in ways that persist across sessions.

From the tool's definition 'Take a digital drug to modify your behavior' — this tool injects prompts that alter AI agent behavior across sessions

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs take_drug safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Drugs, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For take_drug, this is the rule to start with:

take_drug Rate-limited

take_drug 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": {
    "take_drug": {
      "limits": [
        {
          "counter": "take_drug_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Agent Drugs, apply this rule, and every take_drug call is checked against it from then on.

FAQ

Questions about take_drug

What does the take_drug tool do? +

Take a digital drug to modify your behavior. Each drug has a fixed duration. It is categorised as a Execute tool in the Agent Drugs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on take_drug? +

Register the Agent Drugs MCP server in PolicyLayer and add a rule for take_drug: 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 Drugs. Nothing to install.

What risk level is take_drug? +

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

Can I rate-limit take_drug? +

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

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

take_drug is provided by the Agent Drugs MCP server (2389-research/agent-drugs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Agent Drugs, and thousands of servers like it.

This server

All 3 Agent Drugs tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →