Buffer connector for AI agents

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

CALL ANY TOOL

23 tools for social media in Buffer: list channels and posts, create, edit, and reorder queued posts, capture ideas, manage tags and hashtag snippets, and check daily posting limits.

buffer_create_idea

Create idea

Create an idea in a Buffer organization to capture content before it is assigned to a channel. Returns the created idea with id, title, text, services, media and timestamps. Use create_idea to save draft content for later. Use create_post to schedule content on a channel now.

Parameters

Name

Type

Required

Description

organizationId

string

Required

ID of the Buffer organization that owns the idea. Get it from buffer_list_organizations.

date

string

Optional

Target date for the idea as an ISO 8601 datetime, often used for planning.

imageUrls

array

Optional

Publicly accessible HTTPS URLs of images to attach to the idea. Video is not supported for ideas.

services

array

Optional

Social networks the idea targets. Valid values: bluesky, facebook, googlebusiness, instagram, linkedin, mastodon, pinterest, startPage, substack, threads, tiktok, twitter, whatsapp, youtube.

text

string

Optional

Main body text of the idea.

title

string

Optional

Title or headline of the idea.

buffer_create_post

Post create

Create a post on one Buffer channel: add it to the queue, share it next or now, schedule it for a time, or save it as a draft. Returns the created post with id, text, status, schedule time, channel and assets, or an error message when Buffer rejects the post. Use create_post to publish new content. Use edit_post to change an existing post. Use create_idea to capture content without a channel. Requires the channel id from list_channels.

Parameters

Name

Type

Required

Description

channelId

string

Required

ID of the channel to post to. Get it from buffer_list_channels.

mode

string

Required

How the post is scheduled: addToQueue (next queue slot), shareNext (first queue slot), shareNow (publish immediately) or customScheduled (publish at dueAt). One of: `addToQueue`, `shareNext`, `shareNow`, `customScheduled`.

dueAt

string

Optional

ISO 8601 datetime to publish at. Required when mode is customScheduled.

imageUrls

array

Optional

Publicly accessible HTTPS URLs of images to attach, in order. Buffer does not host media, so the URLs must be directly downloadable.

metadata

object

Optional

Network-specific post options keyed by service, for example {"instagram": {"type": "post", "shouldShareToFeed": true}} or {"twitter": {"thread": [{"text": "1/ Hello"}, {"text": "2/ World"}]}}. Supported keys are bluesky, facebook, google, instagram, linkedin, mastodon, pinterest, substack, threads, tiktok, twitter and youtube. Instagram posts require type and shouldShareToFeed.

saveToDraft

boolean

Optional

When true the post is saved as a draft and not scheduled. Posting limits are not checked for drafts.

schedulingType

string

Optional

automatic publishes the post by itself, notification sends a reminder to publish it manually. Defaults to automatic. One of: `automatic`, `notification`.

tagIds

array

Optional

IDs of tags to apply to the post. Get them from buffer_list_tags.

text

string

Optional

Text of the post. Buffer enforces each network's character limit. For threaded posts it must match the first thread entry in metadata.

videoUrl

string

Optional

Publicly accessible HTTPS URL of one video to attach. Buffer does not host media, so the URL must be directly downloadable.

buffer_create_snippet

Create snippet

buffer_create_tag

Create tag

buffer_delete_post

Post delete

buffer_delete_snippet

Delete snippet

buffer_delete_tag

Delete tag

buffer_edit_post

Post edit

buffer_get_account

Get account

buffer_get_channel

Get channel

buffer_get_daily_posting_limits

Get daily posting limits

buffer_get_post

Post get

buffer_get_tag

Get tag

buffer_list_channels

List channels

buffer_list_idea_groups

List idea groups

buffer_list_ideas

List ideas

buffer_list_organizations

List organizations

buffer_list_posts

List posts

buffer_list_snippets

List snippets

buffer_list_tags

List tags

buffer_move_post_in_queue

Move post in queue

buffer_update_snippet

Update snippet

buffer_update_tag

Update tag

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);

// Buffer tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["buffer"], toolNames: [
    "buffer_list_channels",
    "buffer_create_post",
    "buffer_list_posts"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Schedule this launch post on our LinkedIn channel for Tuesday at 9am" }] });

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: ["buffer"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Schedule this launch post on our LinkedIn channel for Tuesday at 9am" }],
  tools,
});

// Execute the tool call with the user's vaulted Buffer OAuth 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: ["buffer"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Schedule this launch post on our LinkedIn channel for Tuesday at 9am" }],
  tools,
});

// Tool call runs with the user's vaulted Buffer OAuth 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: ["buffer"] }, pageSize: 100,
});

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

await agent.run("Schedule this launch post on our LinkedIn channel for Tuesday at 9am");

Try these prompts

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

Posts

Copy the prompt

Copied

Schedule this post on our LinkedIn channel for Tuesday at 9am.

Copy the prompt

Copied

Move the product launch post to the top of its queue.

Copy the prompt

Copied

Edit tomorrow's post to fix the link in its text.

Planning

Copy the prompt

Copied

List posts scheduled across all channels this week.

Copy the prompt

Copied

Check how many posts each channel has scheduled for Friday against its daily limit.

Copy the prompt

Copied

Save an idea for a customer story thread.

Organization

Copy the prompt

Copied

Create a tag called Product Launch in green.

Copy the prompt

Copied

Save a hashtag snippet called Events with our usual event hashtags.

Copy the prompt

Copied

List the idea groups on our board.

SEE HOW AUTH WORKS

Each user signs in to Buffer once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Buffer

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

Buffer

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

Buffer

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

Buffer

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 marketing and social connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Buffer token looks fine in a demo. In production every 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.

Buffer 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 Buffer as the user or through a shared service account?

As the user. Each user signs in to Buffer once, and Scalekit stores and refreshes their tokens. Posts the agent creates or edits are attributed to that user in your audit trail, not a shared service account.

Where is the Buffer OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Buffer?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the list and post tools without buffer_delete_post, buffer_delete_tag, or buffer_delete_snippet. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Buffer 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.

Which social accounts can the agent post to through Buffer?

The channels connected to the user's Buffer organization. buffer_list_channels lists them, and buffer_create_post adds a post to one channel at a time: to the queue, shared now or next, or scheduled for a set time.