X (Twitter) Reply Network Analyzer

X (Twitter)

Operated by Sourcelane✓ verified

A conversation-network analyzer for X (Twitter) accounts that maps outbound interactions by sampling an account's recent posts (including replies) to identify and rank the accounts it replies to, quotes, retweets, and mentions most; calculates activity breakdown between original posts, replies and self-threads; computes response-time metrics (median, average, and shares within short intervals); measures reply concentration toward top contacts and reply engagement (average likes on replies vs originals); assigns interaction scores based on interaction types and ranks contacts by that score; and returns per-contact interaction records with counts, interaction score and share, timing (median response and first/last interaction), engagement statistics, a sample reply and basic profile metadata. The analyzer counts quotes/retweets/mentions separately, derives a ranked contact list from weighted interactions, measures response delay when the parent post is available, and operates without requiring login or cookies.

Verified Sep 28, 12:10 AM

$0.25

per report

Up to 4 per call. Only pay for results returned; failed calls are refunded.

What people use it for

Influencer relationship mapping — find who an influencer actually engages with before pitching a collaboration
Customer support audits — measure a brand account's reply share and response times to customers
Competitor research — see which partners, customers, and communities a competitor's account is closest to
Sales and outreach — identify the people a decision-maker already talks to for warm introductions
Community and network analysis — detect tight reply clusters, mutual boosting, and engagement pods
Journalism and OSINT — map an account's inner circle from public interactions

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-reply-network-analyzer","params":{"username":"elonmusk","maxTweets":4},"maxResults":10}'

Request params

Field	Type	Required	Description
`username`	string	required	The X (Twitter) account to analyze (with or without @; profile URLs work too).
`maxTweets`	integer	optional	How many of the account's most recent posts (replies included) to sample. More posts give a fuller picture of who they interact with. Capped at 4 per call.
`topN`	integer	optional	How many of the most-interacted-with accounts to output as individual rows (ranked by interaction score).

Each result contains

Field	Type	Description
`type`	string	Type
`analyzedUsername`	string	Analyzed Username
`userId`	string	User Id
`name`	string	Name
`followersCount`	integer	Followers Count
`followingCount`	integer	Following Count
`postsAnalyzed`	integer	Posts Analyzed
`timeRange`	object	—
`breakdown`	object	—
`shares`	object	—
`uniqueAccountsInteractedWith`	integer	Unique Accounts Interacted With
`uniqueAccountsRepliedTo`	integer	Unique Accounts Replied To
`topAccountsShare`	number	Top Accounts Share
`replyConcentration`	string	Reply Concentration
`responseTime`	object	—
`replyEngagement`	object	—
`repliesPerDay`	integer	Replies Per Day
`topRepliedTo`	array	—
`topQuoted`	array	—
`topRetweeted`	array	—
`topMentioned`	array	—

Use X (Twitter) Reply Network Analyzer 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-reply-network-analyzer","params":{"username":"elonmusk","maxTweets":4},"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-reply-network-analyzer",
        "params": {"username":"elonmusk","maxTweets":4},
        "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…