TimeToPost MCP server

TimeToPost MCP server

MCP server for TimeToPost that lets AI agents list accounts, schedule/publish/cancel posts, manage drafts and approvals, run AutoSEO, and read analytics via 32 tools.

Category
访问服务器

README

TimeToPost MCP server

An MCP server that lets AI agents (Claude, etc.) drive TimeToPost: list connected accounts, draft/schedule/publish/cancel posts, run AutoSEO, and read analytics. It's a thin adapter over the existing REST API — every tool calls api.timetopost.co with the caller's token, so all auth, org-scoping, validation and publishing logic is reused (never duplicated).

The exact same 32 tools are exposed identically on both surfaces this package ships alongside — the hosted Streamable HTTP endpoint (backend/src/mcp/server.ts) and this npm/stdio package (mcp/src/tools.ts) — enforced by a CI parity test (backend/src/__tests__/unit/mcp-parity.test.ts).

Tools (32)

Call get_capabilities first — it returns the authoritative, machine-readable map of everything below (lifecycles, idempotency contracts, terminology) and should be trusted over inferences from other tools' raw fields.

Core whoami · get_capabilities · list_integrations · get_tiktok_creator_info · list_boards

Posts & publishing list_posts · get_post · schedule_post · publish_post · cancel_post · publish_thread · scheduler_status

Engine drafts (human-approval queue) create_digest_drafts · create_drafts (alias of create_digest_drafts — same mechanism, name doesn't imply digest-only) · list_drafts · approve_draft · reject_draft

Unified approvals rail list_approvals — READ-ONLY: one call returns everything pending human review across all four automation sources (posts/EngineDraft, trends/Trend-Rider, build-in-public tweet drafts, and warm-lead engager DMs), normalized into a common shape with per-source counts. approve_draft/reject_draft above remain the only MCP-side approval actions (for the posts source); approving a trend, build-in-public or DM item is a dashboard action for now.

Analytics & brands

Note: a "brand" here is a niche/play attribution tag on a post (see list_brands) — unrelated to BrandVoice, the org's single AI writing-style profile used to guide AI content generation. An org has one BrandVoice but can have many brands.

get_engagement_summary · get_optimal_times · get_post_metrics · list_brands · get_engagement_by_tag

AutoSEO (any-blog AI content engine — see .claude/skills / get_capabilities for the full connect → integrate → verify → configure → generate flow) autoseo_connect_site · autoseo_integration_kit · autoseo_verify_site · autoseo_list_sites · autoseo_configure · autoseo_auto_configure · autoseo_propose_topics · autoseo_generate_post

Public docs: https://timetopost.co/mcp

Install (any MCP client — Claude Code, Claude Desktop, Cursor)

Published on npm as timetopost-mcp:

{
  "mcpServers": {
    "timetopost": {
      "command": "npx",
      "args": ["-y", "timetopost-mcp"],
      "env": {
        "TIMETOPOST_API_URL": "https://api.timetopost.co",
        "TIMETOPOST_API_TOKEN": "${TIMETOPOST_API_TOKEN}"
      }
    }
  }
}

Or via the Claude Code CLI:

claude mcp add timetopost \
  -e TIMETOPOST_API_URL=https://api.timetopost.co \
  -e TIMETOPOST_API_TOKEN=<your token> \
  -- npx -y timetopost-mcp

Develop from source

cd mcp
npm install
npm run build   # outputs dist/src/

Point your MCP config at node mcp/dist/src/index.js instead of npx.

Smoke test:

npm run build && TIMETOPOST_API_TOKEN="<jwt>" npm run test:smoke

Prefer zero setup? Use the hosted server (browser OAuth, no tokens)

The hosted Streamable HTTP server is live at https://api.timetopost.co/mcp — add it to any remote-capable MCP client and sign in from the browser (email + 6-digit code). No installation, no token pasting:

claude mcp add --transport http timetopost https://api.timetopost.co/mcp

The OAuth access token it mints is a regular TimeToPost API token — visible and revocable in Settings → API — so org-scoping and plan limits are enforced by the backend exactly as for the web app. This npm package remains the right choice for clients that only speak stdio, or when you want the process local.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选