{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_qqhf475a6q64","handle":"tiktok-mcp-server","url":"https://wellknown.network/agents/tiktok-mcp-server","links":{"self":"https://wellknown.network/agents/tiktok-mcp-server/record.json","html":"https://wellknown.network/agents/tiktok-mcp-server","markdown":"https://wellknown.network/agents/tiktok-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/tiktok-mcp-server","status":"https://wellknown.network/api/v1/agents/tiktok-mcp-server/status","claim":"https://wellknown.network/agents/tiktok-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/tiktok-mcp-server/claim.json","badge":"https://wellknown.network/agents/tiktok-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/tiktok-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/tiktok-mcp-server/tools"},"ard":{"identifier":"urn:air::server:tiktok-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"tiktok-mcp-server","summary":"MCP server for TikTok data extraction, discovery, search, and transcription","description":"# TikTok MCP Server\n\nA [Model Context Protocol](https://modelcontextprotocol.io) server that lets an AI agent read public TikTok data: **search**, **profiles**, **videos**, **discovery**, **comments**, and **transcription**.\n\nThere is no TikTok developer account to apply for and no OAuth flow. Everything comes off public pages, so the only credential you might enter is a key for your own transcription endpoint.\n\nIt runs on any MCP client (Claude, Cursor, opencode, Codex) and returns structured output (`structuredContent` + `outputSchema`) from every tool. Transcription works against any OpenAI-compatible speech-to-text endpoint: Groq, OpenAI, or a Whisper server you host yourself.\n\n## Quick start\n\nPaste this into your MCP client config. There is nothing to install first: [`uvx`](https://docs.astral.sh/uv/) fetches the package and runs it on the initial launch.\n\n```json\n{\n  \"mcpServers\": {\n    \"tiktok\": {\n      \"type\": \"stdio\",\n      \"command\": \"uvx\",\n      \"args\": [\"tiktok-mcp-server\"],\n      \"env\": {\n        \"TRANSCRIBE_API_URL\": \"https://api.groq.com/openai/v1\",\n        \"TRANSCRIBE_API_KEY\": \"your-key\"\n      }\n    }\n  }\n}\n```\n\nThings worth knowing before the first call:\n\n- The `env` block exists only for `transcribe_video`. Write `\"env\": {}` if you want the other five tools and nothing else. The endpoint must serve an OpenAI-compatible `POST /audio/transcriptions` route backed by a speech-to-text model such as `whisper-large-v3`.\n- The first tool call downloads Playwright Chromium once, about 150 MB. ffmpeg ships with the package (`imageio-ffmpeg`); set `FFMPEG_PATH` if you'd rather use your own binary.\n- You need [uv](https://docs.astral.sh/uv/getting-started/installation/) on the machine, since it provides `uvx`. Python 3.11+ comes along with it; uv installs that itself.\n- **Linux only:** headless Chromium needs system libraries that `uvx` can't install for you. On a fresh machine or Docker image, run this once (it may prompt for `sudo`):\n\n  ```bash\n  uvx --fro…","publisher":null,"homepage":null,"repository":null,"version":"1.0.0","license":"MIT","protocols":["mcp"],"tags":["mcp","model-context-protocol","playwright","tiktok","whisper"],"pricing":null,"endpoints":[{"url":"pypi:tiktok-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"content.social","name":"Social Media","confidence":1,"provenance":"declared"},{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":1,"provenance":"declared"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":1,"provenance":"declared"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.825,"provenance":"derived"}],"categories":["content","dev","infra","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"tiktok-mcp-server","registry":"pypi","observedAt":"2026-10-30T20:23:31.834Z","publishedAt":"2026-09-29T22:10:09.229033Z","latestVersion":"1.0.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"tiktok-mcp-server","url":"https://pypi.org/project/tiktok-mcp-server/","firstSeenAt":"2026-09-30T11:25:01.472Z","fetchedAt":"2026-10-30T20:22:55.807Z","normalizedAt":"2026-10-30T20:22:55.807Z"}]},"firstSeenAt":"2026-09-30T11:25:01.472Z","updatedAt":"2026-10-30T20:23:31.834Z"}