Add a code block to a draft
AI agents use substack_add_code_block to create or update resources in Substack MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Substack MCP Server environment.
This tool creates or modifies content (a draft) in a reversible manner. It does not execute code, delete data, or move money. The capability to add code blocks to drafts is a content modification (Write) action.
From the tool's definition "Add a code block to a draft" - the tool modifies draft content by inserting a code block, which is a reversible write operation on Substack content.
Attacks that exploit this kind of access
Add a code block to a draft. It is categorised as a Write tool in the Substack MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Substack MCP Server MCP server in PolicyLayer and add a rule for substack_add_code_block: 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 MCP Server. Nothing to install.
substack_add_code_block 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 substack_add_code_block 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 substack_add_code_block. 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.
substack_add_code_block is provided by the Substack MCP Server MCP server (jessicaruthabbott/my-substack-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →