How to Use the Journalistic Reasoning Prover MCP in Claude Code

Q: How do I add the Journalistic Reasoning Prover to Claude Code as an MCP?

Run the command claude mcp add --transport http journalistic-reasoning-prover -- in your terminal. Make sure all flags come before the server name, and verify the connection by running claude mcp list.

Run SPJ-compliant fact checking directly in your terminal and CI/CD pipelines with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Journalistic Reasoning Prover MCP to Claude Code

Create your Vinkius account to connect Journalistic Reasoning Prover 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 Journalistic Reasoning Prover with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Terminal-Based Source Verification

The `validate_journalistic_reasoning` tool brings programmatic source verification directly to your terminal environment. When running Claude Code, you can pipe draft text or JSON payloads straight into the validation tool to verify experts, studies, and publication years before deploying updates. This CLI-first approach makes it easy to catch hallucinated citations in automated content pipelines. If the tool rejects a payload, the shell exit code reflects the failure, allowing you to block broken builds before they hit your CMS.

Automated Ethical Audits via MCP Server

The `validate_journalistic_reasoning` tool parses your terminal outputs to check for false balance and undisclosed conflicts of interest. Claude Code runs this check as a headless operation, scanning your content against SPJ Code of Ethics and IFCN standards without needing a web interface. Our scriptable verification engine requires independent corroboration from at least two sources for every major claim. When a validation check fails, Claude Code outputs the exact ethical deficiency directly to stdout, allowing you to script automated rollbacks or alerts.

Scriptable Attribution and Conflict Checks

The `validate_journalistic_reasoning` tool validates the who, when, where, and how of every quote and statistic in your markdown files. Claude Code executes these checks via shell commands, processing entire directories of investigative drafts in a single run. If the tool flags an unverified quote or an undisclosed advertiser conflict, you can use standard terminal pipes to redirect the error logs. This lets you integrate strict journalistic standards directly into your git hooks and pre-publish scripts.

Setup guide

Set up Journalistic Reasoning Prover 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 journalistic-reasoning-prover-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http journalistic-reasoning-prover-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 Journalistic Reasoning Prover 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": {
    "journalistic-reasoning-prover-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 Journalistic Reasoning Prover. 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 Journalistic Reasoning Prover 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 Journalistic Reasoning Prover MCP in Claude Code

Run the command `claude mcp add --transport http journalistic-reasoning-prover -- ` in your terminal. Make sure all flags come before the server name, and verify the connection by running `claude mcp list`.

Because Claude Code operates entirely in the terminal, you can run the validation tool inside GitHub Actions or Docker containers. It returns standard exit codes, making it easy to block deployments when drafts fail journalistic verification.

Show me the receipts. The tool forces the agent to extract and verify the specific author, journal, and publication year for every cited study. It stops Claude Code from piping hallucinated or unverified academic references into your production database.

The server is built on the SPJ Code of Ethics and IFCN standards. It checks whether your content offers genuine perspective diversity or simply presents false equivalence, helping Claude Code maintain objective reporting standards in automated feeds.

All draft text and source metadata piped through the CLI are processed in zero-trust, ephemeral V8 Isolate sandboxes on Vinkius via an MCP connection. Your connection is secured with a single endpoint token, and no data is logged or retained after execution.

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