meta-mcp

threads_publish_text

Publishes a text-only Threads post with optional link, poll, GIF, topic tag, or quote. Use it to share short updates, run polls, or add accessible media details to Threads.

Instructions

Publish a text-only post on Threads. Supports optional link attachment, poll, GIF, topic tag, and quote post.

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": {
      "text": "<text>"
    },
    "name": "threads_publish_text"
  }
}

Input Schema

Name	Required	Description
`text`	Yes	Post text (max 500 chars)
`gif_id`	No	GIF ID from GIPHY (id field from GIPHY's API response). GIPHY is currently the only supported GIF provider (Tenor was sunset March 31, 2026).
`alt_text`	No	Alt text for accessibility (max 1000 chars)
`topic_tag`	No	Topic tag for the post (1-50 chars, no periods or ampersands)
`is_spoiler`	No	Mark content as spoiler
`location_id`	No	Location ID to tag (from threads_search_locations)
`poll_options`	No	Poll options (2-4 choices, each 1-25 characters). Creates a poll attachment.
`is_ghost_post`	No	Create a ghost post (auto-archived after 24h). Text-only, and per Meta's docs the only other feature supported alongside it is is_spoiler — do not combine with polls, GIFs, links, topic tags, location, reply approvals, or cross-sharing. Ghost posts also cannot be used to reply to a post.
`quote_post_id`	No	ID of a post to quote
`reply_control`	No	Who can reply
`spoiler_ranges`	No	Up to 10 exact spoiler ranges within text. If omitted and is_spoiler=true, the entire text is marked as a spoiler.
`link_attachment`	No	URL to attach as a link preview card (max 5 links per post)
`crossreshare_to_ig`	No	Also share this post to the user's linked Instagram account as a Story
`enable_reply_approvals`	No	Require replies to be approved before they're published. Not compatible with ghost posts.
`crossreshare_to_ig_dark_mode`	No	Cross-share to Instagram Stories in dark mode

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedv2.2.2Oct 26, 2026

addedInput schema / properties / crossreshare_to_ig

Added value: +{
+  "description": "Also share this post to the user's linked Instagram account as a Story",
+  "type": "boolean"
+}

addedInput schema / properties / crossreshare_to_ig_dark_mode

Added value: +{
+  "description": "Cross-share to Instagram Stories in dark mode",
+  "type": "boolean"
+}

addedInput schema / properties / enable_reply_approvals

Added value: +{
+  "description": "Require replies to be approved before they're published. Not compatible with ghost posts.",
+  "type": "boolean"
+}

changedInput schema / properties / gif_id / description

Previous value: -"GIF ID from GIPHY or Tenor"New value: +"GIF ID from GIPHY (id field from GIPHY's API response). GIPHY is currently the only supported GIF provider (Tenor was sunset March 31, 2026)."

removedInput schema / properties / gif_provider

Removed value: -{
-  "description": "GIF provider (GIPHY or TENOR). Tenor sunsets March 31, 2026.",
-  "enum": [
-    "GIPHY",
-    "TENOR"
-  ],
-  "type": "string"
-}

addedInput schema / properties / is_ghost_post

Added value: +{
+  "description": "Create a ghost post (auto-archived after 24h). Text-only, and per Meta's docs the only other feature supported alongside it is is_spoiler — do not combine with polls, GIFs, links, topic tags, location, reply approvals, or cross-sharing. Ghost posts also cannot be used to reply to a post.",
+  "type": "boolean"
+}

addedInput schema / properties / location_id

Added value: +{
+  "description": "Location ID to tag (from threads_search_locations)",
+  "type": "string"
+}

changedInput schema / properties / poll_options / description

Previous value: -"Poll options (2-4 choices). Creates a poll attachment."New value: +"Poll options (2-4 choices, each 1-25 characters). Creates a poll attachment."

addedInput schema / properties / poll_options / items / maxLength
```
Added value: +25
```
addedInput schema / properties / poll_options / items / minLength
```
Added value: +1
```

addedInput schema / properties / spoiler_ranges

Added value: +{
+  "description": "Up to 10 exact spoiler ranges within text. If omitted and is_spoiler=true, the entire text is marked as a spoiler.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "length": {
+        "exclusiveMinimum": 0,
+        "type": "integer"
+      },
+      "offset": {
+        "minimum": 0,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "offset",
+      "length"
+    ],
+    "type": "object"
+  },
+  "maxItems": 10,
+  "minItems": 1,
+  "type": "array"
+}

First observedv2.0.1Mar 19, 2026

TDQS

B3.4/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full disclosure burden, and it does not say that publishing is a rate-limited write (threads_get_publishing_limit is a sibling), what prerequisites or failure modes exist, or that the created post is public and immediately live. The genuinely useful behavioral detail — ghost-post incompatibilities, spoiler range semantics — lives in the schema, not the description.

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?

Two short sentences, with the core action front-loaded before the optional capability list. The feature enumeration is somewhat redundant with the schema but earns its place as a fast scan of what the tool can do.

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

Completeness3/5

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

For a 15-parameter write tool with no annotations and no output schema, the description is thin: it omits the publish-limit/container workflow, auth expectations, and what a successful call returns or how to retrieve the created post. The schema's rich per-parameter constraints compensate somewhat, leaving it adequate but with clear gaps.

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 description coverage is 100% and each of the 15 parameters is documented in-schema, so the baseline of 3 applies. The description's mention of link attachment, poll, GIF, topic tag and quote post merely echoes which optional features exist rather than adding syntax, defaults, or mutual-exclusion rules beyond the schema.

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?

"Publish a text-only post on Threads" gives a specific verb plus resource, and the "text-only" qualifier separates it from the sibling publishers threads_publish_image, threads_publish_video and threads_publish_carousel without requiring schema inspection. The second sentence enumerates the optional capabilities, so the scope is unambiguous.

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

Usage Guidelines3/5

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

Usage is only implied: "text-only" tells the agent this is the non-media path, but the description never explicitly routes to threads_publish_image/video/carousel for media, nor does it mention the publishing-limit or container-status flow used by adjacent threads tools. An agent can infer the use case but gets no when-not guidance.

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

Deploy Server