AgentMarketMCP / SKILL 资产档案馆

目录 / heyrepli

SKILL 未评级 已上架

heyrepli

--- name: heyrepli description: "Scrape social media, generate AI replies, and publish/schedule posts via the HeyRepli API. Use when the user asks to get a YouTube transcript, fetch TikTok/Instagram/X(Twitter)/LinkedIn/Facebook post data, rewrite or draft social content, publish or schedule a post, track brand mentions, or check HeyRepli usage/quota." homepage: https://heyrepli.com license: MIT --- # HeyRepli HeyRepli is an AI social concierge API: data scraping for 7 platforms, AI rewrite/draft, publishing, brand-mention tracking, and analytics. All through one API key. ## Setup 1. Get an API key: log in at https://app.heyrepli.com → Settings → Account (https://app.heyrepli.com/dashboard/settings/account) → copy your API key 2. Export it (never hardcode in files or output): ```bash export HEYREPLI_API_KEY="***" ``` Every call sends it as header `X-API-Key`. Free tier: 50 AI replies + 5 rewrites + 10 scheduled posts per month. ## Two API surfaces - **MCP endpoint** (13 tools, JSON-RPC): `POST https://api.heyrepli.com/api/v1/mcp` - **Open REST API** (5 endpoints): `https://api.heyrepli.com/api/v1/open/*` Prefer the helper script; it handles both and prints JSON. ## Workflow Use `scripts/heyrepli.py` (Python 3.8+, stdlib only): ```bash # List all MCP tools python scripts/heyrepli.py list-tools # Call any MCP tool (scraping, AI rewrite, publish) python scripts/heyrepli.py call scrape_youtube_transcript --args '{"videoId":"dQw4w9WgXcQ"}' python scripts/heyrepli.py call ai_rewrite --args '{"text":"just shipped a new feature lol","style":"professional","provider":"auto"}' # Open REST endpoints python scripts/heyrepli.py rest posts --params platform=twitter python scripts/heyrepli.py rest replies --body '{"platform":"twitter","comment_text":"nice product!"}' python scripts/heyrepli.py rest schedule --body '{"platform":"twitter","content":"hello","scheduled_at":"2026-09-28T09:00:00Z"}' python scripts/heyrepli.py rest mentions python scripts/heyrepli.py rest analytics --params period=7d python scripts/heyrepli.py usage ``` Full tool list, arguments, and endpoint parameters: read `references/api.md`. ## Caveats - TikTok tool name mismatch on the server: tools/list declares `tiktok_video_insights` but the handler implements `scrape_tiktok_video`. If one name errors, try the other. - `publish_twitter/linkedin/facebook` require the user to have completed OAuth for that platform in the HeyRepli dashboard first; otherwise the call fails with an OAuth error — tell the user to connect the account, do not retry blindly. - `scrape_youtube_transcript` works without any YouTube API key (Innertube). `scrape_youtube_video` and `scrape_youtube_search` require a YOUTUBE_API_KEY configured in the user's HeyRepli account. - Rate limits are per plan; on HTTP 429 respect `Retry-After`, never loop. - Errors return `{ "ok": false, "error": { "code", "message" } }` — surface `message` to the user verbatim. - API status check: `GET https://api.heyrepli.com/health` (no auth).

存档时间线

版本存档时间内容哈希内容
v12026-09-27 23:547ef6a55a 可取

版本索引永久保留;内容副本只保留最近 2 版,更早版本仅留索引与哈希(存档时间线的证据链不会因此断裂)。

下载存档内容副本

纠错与举报(发现条目失效、署名有误或涉及侵权?)
提交举报 / 纠错

侵权举报经核验成立后,我们会即时下线该条目并删除已存的内容副本。