AI agents use publish_draft to create or update resources in Substack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Substack environment.
Publishing a draft is a write operation that creates published content on a public platform (Substack). While it modifies state irreversibly in the sense that the post becomes live, it is not a deletion or destructive action—the content remains and can typically be edited or unpublished later. This is categorized as Write rather than Destructive.
From the tool's definition Tool name 'publish_draft' combined with server description stating it 'lets Claude Code...publish posts on your Substack publication.' The server description explicitly lists publishing as a capability alongside create, upload, and schedule operations.
Documented attack patterns abuse exactly the kind of access publish_draft gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Substack, and nothing reaches the server without passing your rules. This is the rule we recommend for publish_draft:
{
"version": "1",
"default": "deny",
"tools": {
"publish_draft": {
"limits": [
{
"counter": "publish_draft_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}publish_draft stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
publish_draft. It is categorised as a Write tool in the Substack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Substack MCP server in PolicyLayer and add a rule for publish_draft: 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 Substack. Nothing to install.
publish_draft is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the publish_draft 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_draft. 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_draft is provided by the Substack MCP server (nanameru/substack-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Substack, 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 Substack tools catalogued and risk-classified — across an index of 43,000+ MCP servers.