Schedule social posts from Gemini

# posterly for Gemini

posterly is the publish layer. Gemini is the chat layer. Add the hosted MCP endpoint as a Spark custom app, then schedule across 18 platforms after the user approves. OAuth sign-in from gemini.google.com is still being validated.

posterly publishes to 18 platforms: Instagram, Facebook, TikTok, X, LinkedIn, YouTube, Pinterest, Threads, Google Business, Telegram, Bluesky, Discord, Slack, Mastodon, Dev.to, Hashnode, WordPress, Lemmy.

## Connect

Gemini web (Spark custom apps): on a computer open gemini.google.com. Settings, Connected Apps, Custom apps, Add a custom app. Paste https://www.poster.ly/api/mcp. If Connected apps is missing, open Personal Intelligence, then Connected apps. Source: https://support.google.com/gemini/answer/17209137

Eligibility: 18 or over, in the US, personal Google Account (not work or school), Keep Activity on, Gemini in English. Connect on the web. Google says the app is then available on mobile and web. Gemini Spark needs Google AI Pro or Ultra: https://support.google.com/gemini/answer/17094507

Work or school accounts: an admin uses Gemini Enterprise (https://support.google.com/g/answer/17106276). Otherwise send the user to https://www.poster.ly/claude, https://www.poster.ly/chatgpt, or https://www.poster.ly/cursor.

Auth: posterly advertises Dynamic Client Registration. Sign-in from gemini.google.com is still being validated. Google documents Advanced features for servers without Dynamic Client Registration; do not assume those fields accept a posterly API key. Do not treat Spark sign-in as confirmed.

Optional Gemini CLI uses the npm stdio server, with flag syntax from https://geminicli.com/docs/tools/mcp-server/: gemini mcp add -s user -e POSTERLY_API_KEY=pst_live_your_key_here posterly npx -y posterly-mcp-server@latest. Replace the placeholder key in your local configuration. The hosted posterly endpoint does not implement streamable HTTP; do not use -t http with it. This CLI setup does not confirm Spark web OAuth.

This is a custom app you add yourself. Do not look for a directory listing.

Gemini web laptop files use the same path as ChatGPT web and Claude.ai: create_media_drop, then the /drop/ page, then list_media. The paperclip is not an upload.

## Are we connected yet?

1. Call `whoami` (no params). Confirm the user, scopes, and workspaces.
2. Call `list_accounts` (`workspace_id` optional). If none are connected, stop and send the user to connect social accounts in posterly. Do not invent account IDs.
3. Prefer `validate_post` before `create_post`. Show the preview. Wait for a clear yes.
4. Only then call `create_post` with `confirm: true`. Never publish or schedule live without that approval.
5. Prefer `scheduled_at` (ISO 8601 UTC) or `find_available_slot` (`account_ids`, `timezone`, `count`). Do not publish immediately unless the user asks.

## Rules

- posterly is the publish layer. This client is the chat or agent layer.
- Never collect card details, posterly passwords, or social-network passwords. Send the user to https://www.poster.ly/agents/signup or https://www.poster.ly/dashboard/api.
- Point to https://www.poster.ly/mcp for the rest of the 59 hosted HTTP MCP tools (62 on the local stdio package).
- After a post is created, send the View in posterly link. Avoid raw JSON dumps unless the user asks to debug.

## Media (honest)

Chat attachments never reach MCP. The paperclip in this chat does not give posterly the file.

The ~4MB limit is the **Vercel request body** on posterly API routes (`/api/mcp`, `POST /api/v1/media/upload`). It is not an MCP protocol cap and not the plan storage cap. Base64 inflates files, so hosted `upload_media` is small images only (relay cap 5MB decoded).

- Public HTTPS URL: `upload_media` with `url` (optional `filename`, `content_type`) or pass `media_url` / `media_urls` on `validate_post` / `create_post`. Server fetch: about 5MB relay, 60MB hard cap. Large R2/S3 URLs fail with `remote_media_too_large`.
- Hosted `upload_media`: required `filename` + `base64_data`. Optional `content_type`. Hits the 4MB Vercel body. JPEG, PNG, GIF, WebP, MP4, MOV, WebM. HEIC is unsupported.
- Laptop file in ChatGPT web, Claude.ai, or Gemini web: `create_media_drop` (optional `filename`, optional `max_files`, default 10). Send the user `drop_url` (`https://www.poster.ly/drop/<token>`). They open it with no dashboard login and drop the file. Then `list_media` (`drop_session_id`) and pass `public_url` to `validate_post` / `create_post`. This is not the chat paperclip.
- Larger files, when this client can HTTP PUT: `create_signed_upload` (`filename`, `content_type`, `size`), PUT the raw bytes to the returned `upload_url` (object storage, not a posterly API route) with the returned headers, then pass `public_url` to `create_post`. That PUT does not hit the 4MB body. Plan video caps: Starter 500MB, Pro 750MB, Power 1GB, Agency 4GB.
- This client is hosted HTTP MCP, so there is no local `file_path`. Small images: public URL or base64 `upload_media`. Laptop video: `create_media_drop` then `list_media`. PUT after `create_signed_upload` only if this runtime can PUT (Cursor Cloud, Codex HTTP).

## Starter tools

- `whoami` (none): Call first. Returns the authenticated user, API key scopes, and workspaces.
- `list_accounts` workspace_id?: Connected social accounts. Stop if this is empty and send the user to connect accounts in posterly.
- `validate_post` account_id or username+platform, caption, scheduled_at?, media_url?, media_urls?, post_type?, workspace_id?: Dry run. Does not create a post. Use this before showing a preview.
- `create_post` same as validate_post, plus confirm: true (required): Destructive write. Refuse unless the user clearly approved caption, account, media, and schedule.
- `upload_media` filename, base64_data (hosted), or url. content_type optional. Stdio also accepts file_path.: Hosted path is base64 with a decoded file of 5MB or less. With url, posterly fetches a public HTTPS URL into storage (localhost and private IPs are blocked). Chat paperclip files never arrive here.
- `create_signed_upload` filename, content_type, size: Bypasses the Vercel ~4MB API body. Returns upload_url (object storage) and public_url. PUT raw bytes to upload_url, then pass public_url to create_post. Use this when the client can PUT (Cursor, Claude Code, Codex).
- `create_media_drop` filename?, max_files?: Creates a no-login page at https://www.poster.ly/drop/<token>. Send drop_url to the user. ChatGPT web, Claude.ai, and Gemini web laptop files use this, then list_media. Not the chat paperclip.
- `list_media` limit?, drop_session_id?: Newest media assets. After create_media_drop, pass drop_session_id and use public_url on validate_post / create_post.
- `find_available_slot` account_ids?, timezone?, workspace_id?, count?: Always pass timezone explicitly (IANA, e.g. Europe/London). Respects a 1-hour gap.
- `generate_captions` platforms (required), brief?, tone?, count?, mode?, source_caption?: Returns caption options only. It does not schedule or publish.
- `list_posts` status?, platform?, account_id?, workspace_id?, limit?: Upcoming or recent posts. status is scheduled, published, failed, or draft.

## Example prompts

- Using posterly, run whoami, then list_accounts. Tell me which LinkedIn, X, and Instagram accounts are connected.
- Draft one caption for LinkedIn, X, and Instagram about our launch. Show me the drafts and wait.
- Find the next free slot in Europe/London, then run validate_post for a LinkedIn text post. Do not create_post yet.
- After I say yes, create_post with confirm true and send the View in posterly link.
- I have a video on my laptop. Call create_media_drop, send me the /drop/ link, wait, then list_media and validate_post. Do not use the paperclip.
- I have a public image URL. upload_media with url, then validate_post an Instagram image post. Wait for my yes.
- List my scheduled posts for this week and summarise what is already on the calendar.
- Generate three caption options with generate_captions. Do not publish.

## Links

- Human landing: https://www.poster.ly/gemini
- MCP hub: https://www.poster.ly/mcp
- Gemini guide: https://www.poster.ly/guides/gemini-guide
- AI agents: https://www.poster.ly/agents
- Agent signup: https://www.poster.ly/agents/signup