How to Use the CrowdTangle MCP in Claude Code
Pipe CrowdTangle engagement metrics directly into your terminal workflows using Claude Code.
Works with every AI agent you already use
…and any MCP-compatible client
Connect CrowdTangle MCP to Claude Code
Create your Vinkius account to connect CrowdTangle to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Analyze viral metrics via MCP Server
`search_posts_by_keyword` returns relevant posts and comparative performance data straight to stdout. You run a single command in your terminal, and your agent scrapes the current narrative without opening a browser. It pipes this raw data into your local log files. For deeper analysis, it triggers `get_top_performing_posts` to calculate actual versus expected interaction scores. You can set this up as a cron job that alerts your Slack channel when a post exceeds its baseline. The terminal handles the entire pipeline autonomously.
Automate URL spread detection
`get_link_shares` identifies exactly who amplified your target URLs across social networks. Your agent fetches the follower counts and interactions, formatting them as a clean CSV right in your working directory. No manual exports required. When a high-profile account shares the link, the script calls `get_post_details` to pull reaction breakdowns. It grabs the platform-specific metadata and appends it to your database. You build a complete tracking system using pure CLI commands.
Audit tracking lists from the CLI
`list_monitored_lists` exposes your list IDs, names, and platform affiliations directly in your shell session. You can script Claude Code to verify that your tracking groups match your current campaign targets. It flags any lists that are missing key accounts. The agent then runs `get_account_leaderboard` to dump the latest average engagement rates. You can pipe this output into jq or another command-line tool for further processing. Your SRE team gets instant visibility into social performance without touching a dashboard.
Set up CrowdTangle MCP in Claude Code
Prerequisites
- Claude Code CLI installed (
npm install -g @anthropic-ai/claude-code) - Active Vinkius subscription with a valid endpoint token
- 1
Run the add command
Open your terminal and run the command shown on the right. Replace
[YOUR_TOKEN_HERE]with your endpoint token from cloud.vinkius.com. Use--scope userto make it available across all projects. - 2
Verify the connection
Start a Claude Code session and type
/mcpto list connected servers. You should seecrowdtangle-mcpwith a green status indicator. - 3
Start using tools
Ask Claude Code something like "Check my latest CrowdTangle transactions." It will automatically discover and invoke the available CrowdTangle tools.
claude mcp add --transport http crowdtangle-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
Real-time monitoring
Live
visibility into every interaction
Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.
Built-in savings
60%
lower AI costs
Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.
Single dashboard
One
place for every integration
Every tool your AI connects to, managed from a single screen. One account, complete control.
Common questions about CrowdTangle MCP in Claude Code
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the CrowdTangle MCP today
We host it, we monitor it, we maintain it. You just paste one token.