Octopost

Add a post to the queue

queue_post

Add a post to your publishing queue. It will be published automatically during your active hours. Posts require platforms to be specified.

HUMAN APPROVAL: set needs_approval=true when a person should review the post first (anything the user hasn't seen word for word). The post is held as "pending" and nothing is published until a person approves it. Octopost emails the account owner and any approvers one-tap Approve / Reject / Edit links (batched, within about 5 minutes) and shows it in the dashboard. After queueing, tell the user: "It's waiting for your approval; check your email." You can't approve your own posts. The account owner can also set auto-approve rules, in which case the result says the post was auto-approved.

The queue publishes posts in FIFO order (oldest first) at regular intervals during active hours (default: every 4 hours, 9am-8pm). Great for evergreen content and maintaining a regular posting cadence.

Same platform limits and same options as create_post, which documents them in full.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "content": "<content>",
      "platforms": "<platforms>"
    },
    "name": "queue_post"
  }
}

Input Schema

Name	Required	Description
`poll`	No	Poll, 2-4 options (Twitter and Mastodon only). See create_post.
`tiktok`	No	For TikTok. See create_post.
`content`	Yes	The post text.
`accounts`	No	Optional. Which account per network when a platform has several, e.g. {"twitter": "@handle"}. See create_post.
`segments`	No	Optional thread replies (up to 24). See create_post.
`variants`	No	Optional. A different version per network, e.g. {"linkedin": {"content": "..."}}; what it leaves out comes from the main post. See create_post.
`platforms`	Yes	Which platforms to post to. Call list_accounts first to see what's connected.
`video_url`	No	Optional video URL.
`media_urls`	No	Optional images or one video: URLs or {url, alt}. See create_post.
`first_comment`	No	Optional. Posted as the first reply right after the post. See create_post.
`needs_approval`	No	If true, the post is held as "pending" until a person approves it from the emailed link or the dashboard. Default: false (some accounts require approval for every post anyway).
`allow_duplicate`	No	Optional. true to send text already sent to that network within 7 days (refused otherwise). See create_post.
`content_warning`	No	Mastodon content warning.
`idempotency_key`	No	Optional. Unique string for this post: a retry with the same key returns the original post. See create_post.
`primary_platform`	No	Which platform goes first when cross-linking.
`cross_link_enabled`	No	Post to primary_platform first, then share its link on the others. See create_post.
`cross_link_template`	No	Cross-link text, with {platform} and {link}. See create_post.
`mastodon_visibility`	No	Mastodon visibility. Default: public.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: it discloses the pending-hold state, the email notification path with Approve/Reject/Edit links and batching within ~5 minutes, the FIFO publish order, default cadence (every 4 hours, 9am-8pm), the constraint that you can't approve your own posts, and that auto-approve rules may apply. None of this is derivable from the structured hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then cleanly sectioned into a HUMAN APPROVAL block and queue-behavior block. Minor redundancy where the FIFO/cadence point is made twice, but every sentence carries actionable content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 18-parameter mutation with no output schema, the description covers the behaviors an agent most needs and explicitly delegates per-platform limits and option details to create_post. What it omits – the shape of the success result beyond auto-approval state, and error handling – is minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description largely restates the needs_approval semantics already documented in the schema, though it does add value by specifying the instruction to relay to the user after queueing and the self-approval restriction.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (add a post to the publishing queue) plus the defining behavior that separates it from sibling create_post: the post is published automatically during active hours in FIFO order. An agent can distinguish queueing from immediate publishing without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context ('great for evergreen content and maintaining a regular posting cadence') and an explicit rule for selecting needs_approval ('anything the user hasn't seen word for word'). It doesn't explicitly state when to prefer create_post or schedule_post instead, which is the remaining gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Octopost tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?