How to Use the Modash MCP in Claude Code

Q: Can I pipe Modash search results from Claude Code to other CLI tools?

Yes. Claude Code outputs raw JSON from searchyoutube or searchinstagram, allowing you to pipe the data directly into jq, custom bash scripts, or local database seeders.

Q: How do I run automated Modash reports using Claude Code?

You can trigger Claude Code from your terminal to run gettiktokreport on a list of handles, saving the raw analytics files directly to your server's disk.

Q: How do I look up specific interest categories?

Run the listinterests tool. It returns the exact interest IDs matching your search query, which you can then use to filter your creator searches.

Pipe real-time social metrics directly into your terminal pipelines and shell scripts using Claude Code and Modash.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modash MCP to Claude Code

Create your Vinkius account to connect Modash 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.

GDPR Free for Subscribers

Setup Modash with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Terminal-driven influencer discovery

The `search_youtube` tool lets you query creator databases directly from your bash shell. You can run a quick command to trigger the query and pipe the raw JSON output straight into utility scripts. Loading heavy web interfaces becomes completely unnecessary. This headless execution fits perfectly into existing command-line setups. You can filter results using standard terminal tools like jq, grep, or awk. Terminal-bound developers get instant validation without changing windows.

Automated profiling via Claude Code MCP Server

This MCP Server allows Claude Code to act as a headless auditing agent running background checks. You can script weekly audits that trigger `get_tiktok_report` or `get_instagram_report` to track follower growth and engagement shifts over time. Routine profile audits no longer require manual oversight. Claude Code outputs structured logs directly to your stdout. If engagement drops below a specific threshold, your script can trigger alerts or update your database. This turns manual social auditing into a clean, automated background process.

Command-line localization and targeting

By calling `list_locations`, Claude Code instantly retrieves geographic taxonomies for precise campaign targeting. You get quick access to the exact IDs required for precise filtering without leaving your terminal session. Script arguments no longer rely on guesswork. You verify the location and language parameters inline using `list_languages`, then immediately feed those clean IDs into `search_instagram`. Your automated scripts run with verified parameters every single time. The entire setup stays lightweight and fast.

Setup guide

Set up Modash 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 user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see modash-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Modash transactions." It will automatically discover and invoke the available Modash tools.

Terminal

claude mcp add --transport http modash-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Modash MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "modash-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Modash. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Modash now

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 Modash MCP in Claude Code

Yes. Claude Code outputs raw JSON from `search_youtube` or `search_instagram`, allowing you to pipe the data directly into jq, custom bash scripts, or local database seeders.

You can trigger Claude Code from your terminal to run `get_tiktok_report` on a list of handles, saving the raw analytics files directly to your server's disk.

Yes. Because it runs entirely in the terminal, you can execute Claude Code commands inside tmux sessions, background jobs, or CI/CD pipelines without needing a GUI.

Run the `list_interests` tool. It returns the exact interest IDs matching your search query, which you can then use to filter your creator searches.

Your credentials reside inside your secure local shell environment variables. All raw social profile data and audience reports are processed entirely within your local terminal environment, keeping your competitive research safe from external logging.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript