MCP tool

check_guardrails

Check a caption against the rules

Reads only · changes nothing, and needs no approval.

What it does

Dry-run a caption against this workspace's brand guardrails (banned words/topics, link policy, posting cap) WITHOUT creating a post. Use this to fix a draft before create_post instead of burning a rejection. Returns { allowed, violations[], rules_checked[], rules_skipped[] }. READ rules_checked BEFORE REPORTING A PASS. An empty rules_checked means this project has NO guardrails configured, so allowed: true says nothing objected — not that the caption was checked and cleared. Saying "it passed the brand rules" about a project with an empty list is a claim nothing verified. rules_skipped lists rules that were asked and could not answer (the topic and tone classifiers fail OPEN by design); a clean verdict listing any of those is an incomplete check, not a pass.

Arguments

Name	Type	Required	What it is
caption	string	Yes	The draft post text

Calling it

Any MCP client calls this by name once the connector is added. The address is the same for every tool:

https://xpost.to/api/mcp

A client that has signed in sends the tool name and its arguments:

{
  "name": "check_guardrails",
  "arguments": {
    "caption": "…"
  }
}

The other tools

get_projectProject rules and settings list_accountsList connected accounts get_posting_rulesPosting rules per account get_upload_ticketGet a one-file upload slot upload_mediaAttach a picture, video or PDF create_postCreate a post list_postsList posts delete_postDelete a post update_postEdit a post retry_deliveryRetry a failed delivery take_down_postTake a live post down list_connection_issuesList account connection problems get_delivery_receiptDelivery receipt for a post bulk_postCreate several posts at once get_post_metricsMetrics for a post get_insightsAccount insights get_top_postsTop posts get_best_timesBest times to post

Back to the MCP connector · What the MCP server is · Connect your assistant