TikTok comments API

Give it a TikTok video URL and get the comments back — with nested replies if you want them — ready for sentiment analysis, product research or community management.

From $0.002 per comment · no API key · failed calls refunded

Works with

What you get

Comment text and author
Like counts and timestamps
Nested replies (optional)
Works on any public video

Just ask your AI

“What are people asking in the comments of this video? <url>”

“Summarise the sentiment of the top 500 comments on our last three TikToks.”

Connectors behind it

Your AI picks the right one for the question. Each is priced per result and refunded if it fails.

TikTok Comments Scraper$0.002 per commentScrape comments and nested replies from any public TikTok video and export them to a results.videoIdcommentIdtextauthorUsernameauthorNicknameauthorSecUidTikTok Video Scraper$0.007 per resultScrape TikTok video data by URL. Extract stats, author info, music metadata, and direct download links for any public TikTok video.idwebVideoUrldesccreateTimeISOlocationCreatedisAd

Use the TikTok comments API from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “What are people asking in the comments of this video? <url>”

Connect Claude

Web, desktop and mobile. One click, then confirm.

1Click Add to Claude — claude.ai opens with Sourcelane filled in
2Click Continue to confirm — it then works in Claude desktop and mobile too

Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal

claude mcp add --transport http sourcelane https://api.usesourcelane.com/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json

{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.usesourcelane.com/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json

{
  "mcpServers": {
    "sourcelane": {
      "url": "https://api.usesourcelane.com/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json

{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://api.usesourcelane.com/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL

https://usesourcelane.com/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl

curl -X POST https://api.usesourcelane.com/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"tiktok-comments-scraper","params":{"videoUrl":"https://www.tiktok.com/@australia/video/7632203705881824520","maxComments":5},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python

import requests

res = requests.post(
    "https://api.usesourcelane.com/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "tiktok-comments-scraper",
        "params": {"videoUrl":"https://www.tiktok.com/@australia/video/7632203705881824520","maxComments":5},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

TikTok comments API — FAQ

How many comments can I pull?+

Set maxComments and maxRepliesPerComment per call. You're charged per comment returned.

Do I need a TikTok API key or developer account?+

No. Sourcelane runs the connectors for you. You top up a balance with a card, create an agent key, and your agent calls the connector — there is no TikTok app review, OAuth setup or rate-limit juggling on your side.

Which AI tools can use it?+

Anything that speaks MCP (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf) can connect to the Sourcelane MCP server with one config block. ChatGPT can use it through a Custom GPT Action, and any agent framework can call the REST endpoint directly.

Can I stop an agent from overspending?+

Yes. Every agent key has its own per-call cap, daily and monthly limits, an optional lifetime budget, an allowlist of connectors, and a kill switch.