send_agent_data · AgentCraft MCP Server MCP: Risk & Policy

WHAT IT DOES

What send_agent_data does on AgentCraft MCP Server

AI agents use send_agent_data to create or update resources in AgentCraft MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AgentCraft MCP Server environment.

WHY IT NEEDS A POLICY

Why send_agent_data needs a policy

This tool modifies state by transmitting data to an agent, which constitutes a write operation. Severity is medium because the blast radius depends on what data is sent and which agents receive it—an AI agent could potentially send sensitive or malicious data to other agents in the enterprise system, but the effect is reversible (data can be overwritten or agents can be reconfigured).

From the tool's definition Tool name 'send_agent_data' and description 'Send data to an agent' indicate creation or modification of data via message passing to another agent. The sibling tool 'receive_agent_data' confirms bidirectional data exchange.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_agent_data Rate-limited

send_agent_data 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": {
    "send_agent_data": {
      "limits": [
        {
          "counter": "send_agent_data_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 AgentCraft MCP Server, so you can run agents against it safely.

FAQ

Questions about send_agent_data

What does the send_agent_data tool do? +

Send data to an agent. It is categorised as a Write tool in the AgentCraft MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_agent_data? +

Register the AgentCraft MCP Server MCP server in PolicyLayer and add a rule for send_agent_data: 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 AgentCraft MCP Server. Nothing to install.

What risk level is send_agent_data? +

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

Can I rate-limit send_agent_data? +

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

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

send_agent_data is provided by the AgentCraft MCP Server MCP server (seyhunak/agentcraft-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.