Publish entity customizations or all customizations in Dataverse
AI agents invoke publish-customizations to trigger actions in PowerPlatform 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.
Publishing customizations triggers an external operation in Dataverse that activates and deploys configuration changes across the environment. This is not a simple write (it doesn't just create/modify data) but rather an operational action that pushes customizations live, potentially affecting all users and system behavior.
From the tool's definition Publish entity customizations or all customizations in Dataverse
Documented attack patterns abuse exactly the kind of access publish-customizations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PowerPlatform MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for publish-customizations:
{
"version": "1",
"default": "deny",
"tools": {
"publish-customizations": {
"limits": [
{
"counter": "publish-customizations_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} publish-customizations 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.
Publish entity customizations or all customizations in Dataverse. It is categorised as a Execute tool in the PowerPlatform MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PowerPlatform MCP server in PolicyLayer and add a rule for publish-customizations: 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 PowerPlatform MCP. Nothing to install.
publish-customizations 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 publish-customizations 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 publish-customizations. 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.
publish-customizations is provided by the PowerPlatform MCP server (michsob/powerplatform-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PowerPlatform 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.
66 PowerPlatform MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.