Compare draft content against published posts to find similar content
AI agents call compare_draft to retrieve information from Jekyll MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and analyzes content from both drafts and published posts to identify similarities. It performs no creation, modification, deletion, execution, or financial operations. The comparison is a read-only analytical function that does not alter the blog's state. Severity is low because misuse would only surface data that already exists in the blog system.
From the tool's definition Tool 'compare_draft' compares draft content against published posts; this is a retrieval and analysis operation with no modification of any data ('compare' indicates side-effect-free analysis).
Attacks that exploit this kind of access
Compare draft content against published posts to find similar content. It is categorised as a Read tool in the Jekyll MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jekyll MCP Server MCP server in PolicyLayer and add a rule for compare_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 Jekyll MCP Server. Nothing to install.
compare_draft is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the compare_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 compare_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.
compare_draft is provided by the Jekyll MCP Server MCP server (jottinger/jekyll-mcp-server). 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 →