start-notification-stream

THE RISK

High Risk

Why start-notification-stream needs a policy

This tool executes an action (starting a notification stream) whose effects depend on system state and arguments, but the side effects are reversible and limited in scope (notifications for testing). It does not permanently modify data (not Write/Destructive), retrieve data (not Read), or involve financial transactions (not Financial).

From the tool's definition Tool name 'start-notification-stream' indicates it starts/initiates a process that sends periodic notifications. Description explicitly states it 'Starts sending' notifications, which is an action that triggers external operations.

Documented attack patterns abuse exactly the kind of access start-notification-stream gives an agent:

POLICY

How to control start-notification-stream

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

policy.json

{
  "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.

Create a free account and register OpenProject 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 OpenProject MCP Server tools

Destructive openproject-delete-project Deletes a project from OpenProject. This action is irreversible. Destructive openproject-delete-task Deletes a task (work package) from OpenProject. This action is irreversible. Write openproject-create-project Creates a new project in OpenProject Write openproject-create-task Creates a new task (work package) in an OpenProject project Write openproject-update-project Updates an existing project in OpenProject. Only include fields to be changed. Write openproject-update-task Updates an existing task (work package) in OpenProject. Only include fields to be changed. Read openproject-get-project Gets a specific project by its ID from OpenProject Read openproject-get-task Gets a specific task (work package) by its ID from OpenProject

All 11 OpenProject 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 OpenProject 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 start-notification-stream

What does the start-notification-stream tool do? +

Starts sending periodic notifications for testing resumability. It is categorised as a Execute tool in the OpenProject 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 start-notification-stream? +

Register the OpenProject MCP Server 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 OpenProject MCP Server. Nothing to install.

What risk level is start-notification-stream? +

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

Can I rate-limit start-notification-stream? +

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.

How do I block start-notification-stream completely? +

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.

What MCP server provides start-notification-stream? +

start-notification-stream is provided by the OpenProject MCP Server MCP server (jessebautista/mcp-openproject-smithery). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every OpenProject MCP Server tool call.

Start from OpenProject 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 →