How to Use the Deep Talk MCP in Claude Code

Q: How do I configure the Deep Talk MCP Server in Claude Code?

Run claude mcp add --transport http deep-talk -- in your terminal. Make sure all flags come before the server name. Verify the installation by running claude mcp list.

Q: Can I use Claude Code to check my Deep Talk account limits?

Yes. Your terminal scripts can execute getaccountdetails to verify remaining processing credits. This prevents automated pipelines from crashing due to rate limits.

Q: How does Claude Code handle Deep Talk dataset metadata?

The CLI uses getdatasetmetadata to check if NLP clustering has completed. You can write a polling script that loops this tool until the dataset is ready for extraction.

Q: Will Claude Code let me list all Deep Talk analysis datasets?

It executes listanalysisdatasets to return record counts and processing statuses as raw JSON. You can pipe that output directly into jq for further terminal processing.

Pipe Deep Talk MCP Server data directly into your terminal workflows 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 Deep Talk MCP to Claude Code

Create your Vinkius account to connect Deep Talk 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 Deep Talk with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Zendesk ingestion checks

Running `list_connected_sources` inside your terminal pulls the exact synchronization status of your external platforms. You set up a cron job that pings Claude Code every hour. The agent checks the data volume ingested and alerts your Slack channel if the Zendesk sync fails. Tracking internal job queues happens entirely headless. Your pipeline triggers `list_processing_tasks` to read completion percentages on active NLP tasks. If an ingestion job hangs at 99%, the script automatically flags the anomaly in your logs.

Pull sentiment metrics via CLI

The MCP tool outputs the exact distribution of negative and positive scores for any dataset via `get_sentiment_analytics`. You pipe this data into a weekly automated report. Claude Code grabs the numbers, formats them into a CSV, and pushes the file to your cloud storage. Extracting core themes requires zero UI interaction. The agent fires `list_extracted_topics` to pull prevalence and importance scores. You can write a bash script that searches for specific terms using `search_topics_by_keyword`, failing the CI build if critical bug mentions spike.

Query Deep Talk MCP Server clusters

Executing `list_conversation_clusters` returns semantically grouped conversations and their representative keywords. Your DevOps scripts pull these cluster sizes to monitor sudden shifts in support ticket categories. It happens fast, right in your SSH session. Validating your available analysis tools takes one command. Claude Code runs `list_available_nlp_models` to ensure the correct sentiment clusterers are active before kicking off a massive data run. It verifies the environment state instantly.

Setup guide

Set up Deep Talk 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 deep-talk-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http deep-talk-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 Deep Talk 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": {
    "deep-talk-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 Deep Talk. 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 Deep Talk 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 Deep Talk MCP in Claude Code

Run `claude mcp add --transport http deep-talk -- ` in your terminal. Make sure all flags come before the server name. Verify the installation by running `claude mcp list`.

Yes. Your terminal scripts can execute `get_account_details` to verify remaining processing credits. This prevents automated pipelines from crashing due to rate limits.

The CLI uses `get_dataset_metadata` to check if NLP clustering has completed. You can write a polling script that loops this tool until the dataset is ready for extraction.

It executes `list_analysis_datasets` to return record counts and processing statuses as raw JSON. You can pipe that output directly into `jq` for further terminal processing.

The connection handles raw customer support transcripts and sentiment metadata. Vinkius issues a single endpoint token for authentication, keeping your API keys out of your local `~/.claude.json` file.

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