How to Use the KnowFirst MCP in Claude Code

Q: How do I connect Claude Code to the KnowFirst MCP server?

Run claude mcp add --transport http knowfirst -- in your terminal, replacing with the one provided by Vinkius. Use claude mcp list to confirm it's connected. Your tools are then ready for headless execution.

Q: How can I get raw data points for an entity with KnowFirst and Claude Code?

First, find your entity ID using searchintelligenceentities. Then, pipe that ID to a command like claude mcp exec knowfirst listentitydatapoints --entityid ID. You'll get the raw data points as a JSON stream in your terminal.

Q: What's the best way to see market trends in the terminal?

A simple command works best: claude mcp exec knowfirst getmarketintelligencetrends --category Finance jq .. This pipes the JSON output from the tool directly into jq for easy filtering and formatting.

Pipe market intelligence directly into your terminal. Connect Claude Code to KnowFirst for headless data analysis and automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KnowFirst MCP to Claude Code

Create your Vinkius account to connect KnowFirst 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 KnowFirst with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Intelligence for Your Shell Scripts

Use `search_intelligence_entities` right from your command line to find entity IDs. You can pipe these IDs directly into another command that calls `get_entity_profile`, creating powerful one-liners for data extraction and analysis. This isn't about a chat interface. It's about making KnowFirst's data available as a standard stream that you can redirect, filter with `jq`, or use as input for other command-line tools. It's built for automation.

Automate Audits in Your CI/CD Pipeline

Set up a cron job or a GitHub Action that uses Claude Code to run `audit_entity_changes` on a schedule. You can write a simple shell script to check for modifications to key entities and trigger an alert if something is off. By connecting to this MCP server, KnowFirst becomes a verifiable step in your deployment or monitoring workflow. You can programmatically ensure data integrity without any manual checks.

Headless Data Source Monitoring

Before a critical job runs, use a script to call `check_knowfirst_api_status` and `search_data_sources`. This confirms the API is online and the sources you depend on are available. It's a simple way to prevent failed pipeline runs. Because Claude Code is a CLI, you can easily integrate these pre-flight checks into any automated process. You get reliable, scriptable access to the operational status of your intelligence data.

Setup guide

Set up KnowFirst 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 knowfirst-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http knowfirst-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 KnowFirst 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": {
    "knowfirst-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 KnowFirst. 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 KnowFirst 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 KnowFirst MCP in Claude Code

Run `claude mcp add --transport http knowfirst -- ` in your terminal, replacing `` with the one provided by Vinkius. Use `claude mcp list` to confirm it's connected. Your tools are then ready for headless execution.

Yes, it's designed for that. Once you've configured the connection in your `~/.claude.json`, you can run Claude Code in any headless environment, including Docker, for CI/CD or other automated tasks using KnowFirst data.

First, find your entity ID using `search_intelligence_entities`. Then, pipe that ID to a command like `claude mcp exec knowfirst list_entity_data_points --entity_id [ID]`. You'll get the raw data points as a JSON stream in your terminal.

A simple command works best: `claude mcp exec knowfirst get_market_intelligence_trends --category Finance | jq .`. This pipes the JSON output from the tool directly into `jq` for easy filtering and formatting.

Your connection uses a unique, short-lived token for authentication. The data in transit, like raw entity data points or connection graphs you request, is encrypted. Vinkius doesn't log the content of your queries or the specific intelligence data returned to your terminal.

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