Skip to main content
Glama
navidmoazzez

Threads MCP

by navidmoazzez

Publish a chain of posts

create_thread
Destructive

Publish a multi-post thread on Threads as a chain of replies, validating every part before the first post goes out. Requires explicit confirmation because the result is public and cannot be undone.

Instructions

Publish several posts as a thread, each replying to the one before. Threads has no thread endpoint: a thread is a chain of ordinary posts, so it can half-publish. Every part is length-checked before the first one goes out, and if a later part still fails the error names exactly how far it got. Public and irreversible, so this needs confirm: true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
postsYesThe parts, in order. Each is capped at 500 characters and validated before anything is published.
accountNoWhich connected Threads profile to act as, by username (for example 'thenavidm'). Defaults to the first connected profile. Call list_accounts to see them.
confirmNoMust be true for this to run. The result is public immediately or cannot be undone, so it is refused without an explicit confirmation. Threads has no edit endpoint and no unsend.
alt_textNoAlt text for the attached image or video.
image_urlNoPublic HTTPS URL of a JPEG or PNG, 8MB or less. Threads fetches it itself; there is no upload endpoint.
topic_tagNoOne topic tag, without the #. 1-50 characters, no periods or ampersands.
video_urlNoPublic HTTPS URL of an MP4 or MOV, up to 1GB and 5 minutes.
reply_to_idNoStart the thread as a reply to this post, rather than as a new one.
reply_controlNoWho may reply. Defaults to everyone.
link_attachmentNoA URL to render as a preview card. Text-only posts only; it cannot be combined with media.
Install Server

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true, but the description adds substantial behavioral detail: the operation can half-publish, all parts are length-checked before the first post goes out, failures name how far publishing got, and the result is public and irreversible. This meaningfully exceeds annotation-only information.

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

Conciseness5/5

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

The description is compact: three dense sentences, each earning its place. It front-loads the purpose, then covers the critical partial-failure behavior, then the confirmation requirement. No filler or redundancy.

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

Completeness5/5

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

Despite having 10 parameters and no output schema, the description is sufficient for correct invocation. The schema covers all parameter meanings, while the description supplies the critical operational context: partial publishing, validation ordering, failure reporting, and the mandatory confirm flag. Nothing essential for safe invocation is missing.

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% and the schema already documents every parameter and the confirm requirement. The description mentions 'needs confirm: true' but that only restates the schema. It adds no new parameter-level semantics beyond what the structured schema provides.

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 ('publish'), a precise resource ('several posts as a thread'), and the mechanism ('each replying to the one before'). It further clarifies that a thread is just a chain of ordinary posts, distinguishing this from a dedicated thread resource.

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?

The description clearly signals when to use this tool: when publishing multiple posts as a reply chain. It gives useful context about Threads having no thread endpoint, but it does not explicitly name alternatives or state when not to use it.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/navidmoazzez/threads-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server