Typefully connector for AI agents

Tools your social media agent reaches for on Typefully, scoped per user.

CALL ANY TOOL

18 tools for social media in Typefully: create, edit, and schedule drafts, manage queues and tags, and run comment threads on drafts.

typefully_add_comment_to_thread

Add comment to thread

Reply on an existing comment thread of a draft. Returns the full thread with its id, platform, status, selected text and all comments including the new one. Use it to answer review feedback. Use create_comment_thread to start a thread on new text. Needs comment_thread_id from list_comment_threads.

Parameters

Name

Type

Required

Description

comment_thread_id

string

Required

UUID of the comment thread on the draft. Get it from typefully_list_comment_threads.

draft_id

integer

Required

Numeric ID of the draft. Get it from typefully_list_drafts or from the response of typefully_create_draft.

social_set_id

integer

Required

Numeric ID of the Typefully social set (connected account profile) to act on. Get it from typefully_list_social_sets.

text

string

Required

Plain-text body of the reply, up to 10000 characters.

typefully_create_comment_thread

Create comment thread

typefully_create_draft

Create draft

Create a draft, scheduled post or immediate post in a social set. Returns the new draft with its id, status, publish_state, private URL, platform posts and scheduling fields. Use it to write posts for one or more platforms. Set publish_at to schedule or publish, or leave it empty to save a draft. Use update_draft to change an existing draft. Needs social_set_id from list_social_sets; any tags must already exist (see list_tags).

Parameters

Name

Type

Required

Description

platforms

object

Required

Platform settings keyed by platform name: x, linkedin, mastodon, threads, bluesky or substack. Each platform you want to post to takes enabled set to true and a posts array, where every post has a text and may carry media_ids. Each array entry is one post, so several entries make a thread. Platform extras are optional: x posts accept reply_settings and quote_post_url, and x settings accept reply_to_url or community_id; linkedin settings accept first_comment. A platform set to enabled false needs no posts. Example: {"x": {"enabled": true, "posts": [{"text": "Launching today"}, {"text": "Details in the thread"}]}, "linkedin": {"enabled": true, "posts": [{"text": "Launching today"}]}}.

social_set_id

integer

Required

Numeric ID of the Typefully social set (connected account profile) to act on. Get it from typefully_list_social_sets.

draft_title

string

Optional

Internal title for organising drafts in Typefully. It is never posted to social media. Up to 512 characters.

plan_at

string

Optional

Date to plan the draft for: next-free-slot or a future ISO 8601 datetime with a timezone offset. A planned draft appears on the queue and calendar but never publishes until you confirm it by setting publish_at. Cannot be combined with publish_at.

publish_at

string

Optional

When to publish: the word now to publish immediately, next-free-slot for the next queue slot, or a future ISO 8601 datetime with a timezone offset. Leave empty to keep the item a plain draft. Cannot be combined with plan_at. Publishing with now is asynchronous: the response shows publish_state in_progress, so poll typefully_get_draft until it is finished.

scratchpad_text

string

Optional

Plain-text notes attached to the draft for your own reference. Formatting is stripped and the text is never posted.

boolean

Optional

Set true to generate a public share URL that lets anyone with the link view the draft. The API default is false.

tags

array

Optional

Tag slugs (not display names) to put on the draft, up to 10. Each tag must already exist in the social set; create missing ones with typefully_create_tag. Sending a list replaces the draft's existing tags.

typefully_update_queue_schedule

Update queue schedule

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Typefully tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["typefully"], toolNames: [
    "typefully_list_social_sets",
    "typefully_create_draft",
    "typefully_get_queue"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Draft a thread announcing our new API and schedule it in next week's queue" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["typefully"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Draft a thread announcing our new API and schedule it in next week's queue" }],
  tools,
});

// Execute the tool call with the user's vaulted Typefully access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["typefully"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Draft a thread announcing our new API and schedule it in next week's queue" }],
  tools,
});

// Tool call runs with the user's vaulted Typefully access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["typefully"] }, pageSize: 100,
});

const agent = new Agent({
  name: "social_media_agent",
  model: "gemini-2.5-pro",
  instruction: "Typefully tools scoped to this user",
  tools,
});

await agent.run("Draft a thread announcing our new API and schedule it in next week's queue");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Typefully tool. Click to copy, paste into your agent, done.

Drafts

Copy the prompt

Copied

Draft a thread announcing our new API and schedule it for Tuesday at 10am.

Copy the prompt

Copied

Add the launch tag to my API draft.

Copy the prompt

Copied

List my scheduled drafts.

Queue

Copy the prompt

Copied

Show next week's publishing queue.

Copy the prompt

Copied

Change our posting schedule to weekdays at 9am and 4pm.

Copy the prompt

Copied

Which social sets can I post to?

Review

Copy the prompt

Copied

Comment on the launch draft asking to shorten the first post.

Copy the prompt

Copied

Resolve the open comment threads on the launch draft.

Copy the prompt

Copied

Reply to Dana's comment on the pricing draft.

SEE HOW AUTH WORKS

Each user connects their own Typefully access token once, and Scalekit sends it with every call. Tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Typefully

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Typefully

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Typefully

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Typefully

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other social media and marketing connectors.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Typefully access token looks fine in a demo. In production every draft and scheduled post looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Typefully today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Typefully as the user or through a shared token?

As the user. Each user connects their own Typefully access token once, and Scalekit sends it with every call. Audit logs attribute every draft, scheduled post, and comment to that user, not a shared service account.

Where is the Typefully access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Typefully?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example draft and queue reads without typefully_delete_draft, which deletes a draft permanently. typefully_create_draft can also schedule or publish a post, so leave it out for a review-only agent. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Typefully access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

What is a social set in Typefully?

A social set is a connected account profile. typefully_list_social_sets returns the sets the user's access token can reach, and drafts, queues, posting schedules, and tags all belong to one social set.