X (Twitter) Fake Follower Auditor

X (Twitter)

Operated by Sourcelane✓ verified

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, 12:10 AM

$0.10

per audit report

Up to 10 per call. Only pay for results returned; failed calls are refunded.

What people use it for

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

Trust & reliability

7d uptime trend

Window	Uptime	Success rate	p50	p95
24h	—	—	—	—
7d	—	—	—	—
30d	—	—	—	—

Calling contract

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://cool-puffin-608.convex.site/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

Use X (Twitter) Fake Follower Auditor from Claude, ChatGPT or Cursor

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. Paste one URL.

1Copy your personal connector URL
2In Claude open Settings → Connectors → Add custom connector
3Paste the URL and click Add — done

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://cool-puffin-608.convex.site/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://cool-puffin-608.convex.site/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://cool-puffin-608.convex.site/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://cool-puffin-608.convex.site/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://sourcelane-amber.vercel.app/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl

curl -X POST https://cool-puffin-608.convex.site/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}'

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://cool-puffin-608.convex.site/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"])

Reviews

—

0 reviews

Leave a review

Loading reviews…