AI agents invoke send_raw_api_request to trigger actions in ConnectWise API Gateway MCP Server. 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.
The name implies sending arbitrary raw API requests to ConnectWise Manage, which is an execute-level operation capable of triggering reads, writes, or destructive actions depending on the request. Since the description is empty, exact capabilities are unknown, but raw API access typically allows any HTTP method (GET, POST, PUT, DELETE), making Execute the most appropriate base category.
From the tool's definition Tool name 'send_raw_api_request' and server description mentions 'execution' of API calls; description is empty/uninformative.
Documented attack patterns abuse exactly the kind of access send_raw_api_request gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ConnectWise API Gateway MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for send_raw_api_request:
{
"version": "1",
"default": "deny",
"tools": {
"send_raw_api_request": {
"limits": [
{
"counter": "send_raw_api_request_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} send_raw_api_request 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_raw_api_request. It is categorised as a Execute tool in the ConnectWise API Gateway MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ConnectWise API Gateway MCP Server MCP server in PolicyLayer and add a rule for send_raw_api_request: 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 ConnectWise API Gateway MCP Server. Nothing to install.
send_raw_api_request 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_raw_api_request 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_raw_api_request. 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_raw_api_request is provided by the ConnectWise API Gateway MCP Server MCP server (jasondsmith72/cwm-api-gateway-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ConnectWise API Gateway MCP Server, 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.
11 ConnectWise API Gateway MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.