跳过安装。2 分钟内即可运行。
在 cloud.anythingmcp.com 开始免费试用，一键添加 Buffer，然后将你的 AI 客户端（Claude、ChatGPT、Copilot 或 Cursor）指向生成的 MCP 端点。无需 Docker，无需 git clone，无需任何工程经验。
摘要
通过 Buffer 的 GraphQL API 从任意 AI 代理管理 Buffer（社交媒体排期：组织、频道、帖子、创意）。9 个工具，API key。
试试这样问
Buffer 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Buffer、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Buffer + Gemini
通过 Buffer 的 GraphQL API 从任意 AI 代理管理 Buffer（社交媒体排期：组织、频道、帖子、创意）。9 个工具，API key。
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
BUFFER_ACCESS_TOKEN
步骤 1 — 获取凭证
This connector wraps Buffer's public GraphQL API at https://api.buffer.com (docs: https://developers.buffer.com). It replaces the legacy api.bufferapp.com REST API; Buffer's API is available on every plan, including Free.
Setup:
- Sign in to Buffer and open Settings → API (https://publish.buffer.com/settings/api).
- Click Generate API Key (Personal Access tab). Free accounts can hold one key, paid plans up to five.
- Paste the key into
BUFFER_ACCESS_TOKEN. It is sent asAuthorization: Bearer <key>and acts as your own account: every organization and channel you can see in Buffer, with no per-organization scoping.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
你的服务器 URL： 在 AnythingMCP 中打开 MCP Servers → 此连接器所在的服务器，复制它的 URL（
https://cloud.anythingmcp.com/mcp/…）。本指南中出现YOUR_SERVER_ID的地方都用它替换。
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
"headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Buffer应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
buffer_current_user | Return the authenticated Buffer account (id, email, name, timezone) with the organizations it belongs to |
buffer_list_channels | List the connected social channels (X/Twitter, LinkedIn, Instagram, Facebook, Mastodon, Bluesky, Threads, TikTok, Pinterest, YouTube, …) of… |
buffer_list_posts | List posts of an organization, newest page first, optionally filtered by channel IDs and status |
buffer_create_post | Create a post on ONE channel: add it to the queue, schedule it for a time, publish it now, or save it as a draft |
buffer_update_post | Edit a post that has not been sent yet: text, schedule, media or tags |
buffer_delete_post | Delete a post by ID |
buffer_send_now | Publish a queued or scheduled post immediately instead of at its slot |
buffer_list_ideas | List the ideas (content not yet assigned to a channel) of an organization |
buffer_create_idea | Save an idea in an organization: content you want to publish later, not yet tied to a channel or a time |
buffer_graphql_schema_url | Return the URL of the GraphQL schema (SDL) |
buffer_graphql_schema | Fetch the GraphQL schema: a summary, one type, a search slice or the full SDL |
buffer_graphql_query | Run an arbitrary GraphQL query |
buffer_graphql_mutation | Run an arbitrary GraphQL mutation |
buffer_graphql_subscription | Run an arbitrary GraphQL subscription (if the API supports it) |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?
