Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.
日本語の概要は準備中です。原文の説明を表示しています。
Schedule, publish and analyze social posts across 15 networks via BulkPublish (MCP or REST) — Facebook, Instagram, X, TikTok, YouTube, Threads, Bluesky, Pinterest, Google Business, LinkedIn, Mastodon, Discord, Telegram, Tumblr, Snapchat. Use when the user wants to post, schedule, or bulk-publish to social media, check connected channels, or read post analytics. Always check platform rules before composing.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Cross-platform scheduling and publishing through one API. Unlike per-platform skills, this targets many networks in a single call, with each platform's rules enforced up front.
MCP (recommended) — hosted server, no install:
claude mcp add --transport http bulkpublish https://mcp.bulkpublish.com/mcp
Add it as a custom connector and OAuth 2.1 walks you through consent — no key in the URL.
Or the npm server (stdio):
claude mcp add bulkpublish --env BULKPUBLISH_API_KEY=bp_your_key -- npx -y @bulkpublish/mcp-server
Or plain REST: https://app.bulkpublish.com/api, spec at
https://app.bulkpublish.com/openapi.json, docs at https://app.bulkpublish.com/docs.
Get an API key at app.bulkpublish.com/developer and
send it as Authorization: Bearer <key>. API and MCP access are on every plan, free included.
list_channels — get connected accounts with their channelId and platform. Do this
first; never guess a channel id.get_channel_options) before composing.upload_media takes a public url or a local filePath, and
returns the id you pass in mediaFileIds.create_post with content, channels, and status: "scheduled" plus scheduledAt
(or leave it a draft, then publish_post when the user confirms).content (string, required) — post text
channels (array, required) — [{ channelId: number, platform: string }]
status ("draft" | "scheduled") — default "draft"
scheduledAt (ISO 8601 string) — required when status is "scheduled"
timezone (string) — e.g. "America/New_York"
mediaFileIds (number[]) — ids from upload_media
platformContent (object) — per-platform text override
postTypeOverrides (object) — per-platform post type, e.g. {"instagram":"reel"}
platformSpecific (object) — per-platform extras (titles, link previews)
requestApproval (boolean, false) — hold the post for human review
create_post schedules or drafts. To send something out immediately, create it and then call
publish_post; retry_post re-runs a failed one.
platformSpecific.youtube.title /
platformSpecific.pinterest.title.feed_photo. With a video you must set
postTypeOverrides.instagram to reel or feed_video, or the post fails.platformContent to give the short networks their own
trimmed text rather than truncating everything down to the smallest limit.Posts carry an approvalStatus (none | pending | approved | rejected) separate from
status. The scheduler never publishes a pending or rejected post. Pass
requestApproval: true to hold a post for a human; approve_post / reject_post release it.
API keys whose role lacks post:publish always have it forced on and get 403 APPROVAL_REQUIRED from publish and retry — that is expected, not a bug.
get_analytics takes startDate / endDate (ISO dates) and returns a summary with a
per-platform breakdown; get_post_metrics covers a single post. Outbound linkClicks are
measured by BulkPublish's own short links and are reported separately from clicks — one
visit can appear in both, so never add them together.
get_channel_health (re-auth needed?), get_queue_slot (next optimal time for a timezone),
create_schedule (recurring posts), list_labels, get_quota_usage (plan limits and usage).
list_channels before every publish.まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.
日本語の概要は準備中です。原文の説明を表示しています。
Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.
日本語の概要は準備中です。原文の説明を表示しています。
Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.
日本語の概要は準備中です。原文の説明を表示しています。
Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.
日本語の概要は準備中です。原文の説明を表示しています。
Audit whether a website can be found, crawled, and cited by AI answer engines such as ChatGPT Search, Perplexity, Google AI Overviews, and Microsoft Copilot. Use when someone asks why their brand is missing from AI answers, whether AI crawlers can read their site, how to get cited by ChatGPT or Perplexity, or asks for a GEO or AEO (generative / answer engine optimization) review. Produces a citation baseline across buyer-intent prompts, a crawler-access check, a citability review of named pages, and a ranked fix list. Not for keyword rank tracking, paid search, or pages behind a login.
日本語の概要は準備中です。原文の説明を表示しています。
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
日本語の概要は準備中です。原文の説明を表示しています。