AI agents invoke send-message to trigger actions in Claude Desktop API 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.
This tool triggers external API calls to Claude, executing arbitrary prompts with potentially custom system prompts. The server explicitly advertises bypassing platform limitations, meaning an AI agent could use this to circumvent safety controls, exfiltrate data through a secondary AI channel, or chain prompts in unexpected ways.
From the tool's definition "Send a message to Claude" on a server that "enables Claude Desktop users to access the Claude API directly" and "bypass Professional Plan limitations"
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 Claude Desktop API MCP, 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": 10,
"scope": "grant"
}
]
}
}
}send-message 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.
Free to start. No card required.
Send a message to Claude. It is categorised as a Execute tool in the Claude Desktop API MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Desktop API 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 Claude Desktop API MCP. Nothing to install.
send-message is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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 Claude Desktop API MCP server (mlobo2012/claude_desktop_api_use_via_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Desktop API MCP, 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.
4 Claude Desktop API MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.