Start post viewer (React dashboard with hot reload)
AI agents invoke start_viewer to trigger actions in LinkedIn-Posts-Hunter-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.
Starting a dashboard viewer constitutes executing an operation that launches an external system component. While the tool itself doesn't directly modify or delete data, it initiates a process whose effects depend on subsequent user/system interaction.
From the tool's definition Tool starts a React dashboard viewer with live functionality ('hot reload'). This triggers and runs an external application process.
Documented attack patterns abuse exactly the kind of access start_viewer gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LinkedIn-Posts-Hunter-MCP-Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start_viewer:
{
"version": "1",
"default": "deny",
"tools": {
"start_viewer": {
"limits": [
{
"counter": "start_viewer_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_viewer 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.
Start post viewer (React dashboard with hot reload). It is categorised as a Execute tool in the LinkedIn-Posts-Hunter-MCP-Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LinkedIn-Posts-Hunter-MCP-Server MCP server in PolicyLayer and add a rule for start_viewer: 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 LinkedIn-Posts-Hunter-MCP-Server. Nothing to install.
start_viewer 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_viewer 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_viewer. 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_viewer is provided by the LinkedIn-Posts-Hunter-MCP-Server MCP server (kevin-weitgenant/linkedin-posts-hunter-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LinkedIn-Posts-Hunter-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.
6 LinkedIn-Posts-Hunter-MCP-Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.