Starts sending periodic notifications for testing resumability
AI agents invoke start-notification-stream to trigger actions in Codemesh. 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 falls under Execute rather than Write because it initiates a continuous process/stream rather than simply creating a one-time data record. The tool orchestrates an external operation (notification delivery) whose effects depend on runtime arguments and configuration.
From the tool's definition The tool 'starts sending periodic notifications' which indicates it triggers an ongoing external operation with side effects that depend on how notifications are configured and what they target.
Documented attack patterns abuse exactly the kind of access start-notification-stream gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codemesh, and nothing reaches the server without passing your rules. This is the rule we recommend for start-notification-stream:
{
"version": "1",
"default": "deny",
"tools": {
"start-notification-stream": {
"limits": [
{
"counter": "start-notification-stream_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start-notification-stream 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.
Starts sending periodic notifications for testing resumability. It is categorised as a Execute tool in the Codemesh MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Codemesh MCP server in PolicyLayer and add a rule for start-notification-stream: 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 Codemesh. Nothing to install.
start-notification-stream 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 start-notification-stream 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 start-notification-stream. 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.
start-notification-stream is provided by the Codemesh MCP server (kiliman/codemesh). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codemesh, 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.
13 Codemesh tools catalogued and risk-classified — across an index of 43,000+ MCP servers.