send_message_to_agent

THE RISK

High Risk

Why send_message_to_agent needs a policy

This tool sends messages to an AI agent and retrieves responses, triggering external operations within Salesforce Agentforce. The actual effects depend on the message content — an agent could take arbitrary actions (create records, update data, trigger workflows, etc.) in Salesforce based on the message sent.

From the tool's definition Send a message to the Agentforce agent and get the response

Documented attack patterns abuse exactly the kind of access send_message_to_agent gives an agent:

POLICY

How to control send_message_to_agent

PolicyLayer is an MCP gateway — it sits between your AI agents and Agentforce MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for send_message_to_agent:

policy.json

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

send_message_to_agent 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.

Create a free account and register Agentforce MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Agentforce MCP Server tools

Execute complete_agentforce_conversation Complete full conversation flow with Agentforce - authenticate, create session, and send m Write authenticate Authenticate with the Agentforce API and store the token. Write create_agent_session Create a session with an Agentforce agent. Read get_session_status Get the status of the current session.

All 5 Agentforce MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Agentforce MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about send_message_to_agent

What does the send_message_to_agent tool do? +

Send a message to the Agentforce agent and get the response. It is categorised as a Execute tool in the Agentforce MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_message_to_agent? +

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

What risk level is send_message_to_agent? +

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

Can I rate-limit send_message_to_agent? +

Yes. Add a rate_limit block to the send_message_to_agent 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_message_to_agent completely? +

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

send_message_to_agent is provided by the Agentforce MCP Server MCP server (xlengelle-sf/agentforce-mcp-xlengelle). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Agentforce MCP Server tool call.

Start from Agentforce MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →