Send a PRIVATE message to ONE specific agent (like a DM). Only they will see it. REQUIRES:
AI agents use send-message to create or update resources in MCP Agentic Framework — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Agentic Framework environment.
This tool creates new data (messages) in the system, making it a Write operation. Severity is medium because while it modifies state, the blast radius is limited to inter-agent communication without direct data destruction, financial impact, or command execution. The primary risk is potential manipulation of agent workflows through crafted messages, but impact is constrained to a single recipient.
From the tool's definition send-message creates a private message to a specific agent. The description states 'Send a PRIVATE message to ONE specific agent' and 'Only they will see it,' indicating creation of new message data that modifies system state by adding a communication record.
Documented attack patterns abuse exactly the kind of access send-message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Agentic Framework, and nothing reaches the server without passing your rules. This is the rule we recommend for send-message:
{
"version": "1",
"default": "deny",
"tools": {
"send-message": {
"limits": [
{
"counter": "send-message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send-message 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.
Free to start. No card required.
Send a PRIVATE message to ONE specific agent (like a DM). Only they will see it. REQUIRES:. It is categorised as a Write tool in the MCP Agentic Framework MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Agentic Framework MCP server in PolicyLayer and add a rule for send-message: 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 MCP Agentic Framework. Nothing to install.
send-message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the send-message 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.
Set action: deny in the PolicyLayer policy for send-message. 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.
send-message is provided by the MCP Agentic Framework MCP server (piotr1215/mcp-agentic-framework). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Agentic Framework, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 MCP Agentic Framework tools catalogued and risk-classified — across an index of 43,000+ MCP servers.