Operated by Sourcelane✓ verified
Audit any X (Twitter) account for fake followers and bots - per-follower bot scores, flagged signals, and an audience quality grade.
Audits X (Twitter) accounts for fake followers and bot-driven audience inflation by sampling an account's most-recent followers and scoring each sampled follower on multiple bot signals; produces a quantitative audit summary with a fake-follower percentage, a suspicious-follower percentage, an A–D audience quality grade, a signal breakdown (counts per signal), and sample statistics (verification counts, no-tweet/default-avatar percentages, average follower/following counts), plus full per-follower evidence including a 0–100 bot score, categorical verdicts (likely_fake / suspicious / likely_real), which signals fired, follower/following/tweet counts, account creation date, verification status, and profile URL. The core mechanism samples up to several thousand newest followers, detects signals such as default profile picture, zero tweets, suspicious follow ratios, brand-new accounts (recent creation), spammy handles, empty bios, no cover picture, and public flagged-automated markers; each fired signal contributes a weighted amount to a capped bot score, and verdict thresholds map scores to categorical labels, with the fake-follower percentage computed as the share of sampled followers classified as likely fake.
Verified Sep 28, 3:56 AM
$0.10
per audit report
Up to 10 per call. Only pay for results returned; failed calls are refunded.
Influencer vetting before sponsorships or partnerships
Detecting purchased or suddenly acquired followers
Agency audience audits and creator roster screening
Competitor audience quality comparison within a niche
Brand safety checks to verify partner account audience authenticity
The X account to audit.
Optional settings
| Window | Uptime | Success rate | p50 | p95 | Calls |
|---|---|---|---|---|---|
| 24h | — | — | — | — | 0 |
| 7d | — | — | — | — | 0 |
| 30d | — | — | — | — | 0 |
Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.
Call it via Sourcelane
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"x-fake-follower-auditor","params":{"username":"natgeo"},"maxResults":10}'Request params
| Field | Type | Required | Description |
|---|---|---|---|
username | string | required | The X (Twitter) account to audit (with or without @). |
sampleSize | integer | optional | How many of the account's most-recent followers to sample and score. Larger samples give more accurate fake-follower percentages. Max 5000. |
Each result contains
| Field | Type | Description |
|---|---|---|
recordType | string | Record Type |
auditedUsername | string | Audited Username |
auditedUserId | string | Audited User Id |
followerCount | integer | Follower Count |
sampleSize | integer | Sample Size |
fakeFollowerPct | number | Fake Follower Pct |
suspiciousPct | number | Suspicious Pct |
qualityGrade | string | Quality Grade |
signalBreakdown | object | — |
sampleStats | object | — |
sampledNewestFirst | boolean | Sampled Newest First |
checkedAt | string | Checked At |
Pick your tool and connect in under a minute. Then just ask — for example: “Find the 50 most-liked tweets about 'MCP servers' this month and summarise the takes.”
Connect Claude
Web, desktop and mobile. One click, then confirm.
Adds the Sourcelane MCP server with your key as a header.
claude mcp add --transport http sourcelane https://api.usesourcelane.com/mcp \
--header "Authorization: Bearer sl_live_your_agent_key"Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.
{
"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"
}
}
}
}Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).
{
"mcpServers": {
"sourcelane": {
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer sl_live_your_agent_key"
}
}
}
}Save as .vscode/mcp.json. VS Code prompts for your key once.
{
"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
}
]
}Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.
https://usesourcelane.com/openapi.jsonOne POST. Pass maxResults to cap cost.
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"x-fake-follower-auditor","params":{"username":"natgeo"},"maxResults":10}'Wrap the REST call as a tool, or point an MCP client at the endpoint.
import requests
res = requests.post(
"https://api.usesourcelane.com/v1/call",
headers={"Authorization": "Bearer sl_live_your_agent_key"},
json={
"listing": "x-fake-follower-auditor",
"params": {"username":"natgeo"},
"maxResults": 10,
},
timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])—
0 reviews
Leave a review
Loading reviews…